Source profileQuality 95/100

hua-bang/pulse-agent/.pulse-coder/skills/project-roadmap/SKILL.md

project-roadmap

Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.

Source repository stars
28
Declared platforms
0
Static risk flags
3
Last source update
2026-08-24
Source checked
2026-08-25

Decision brief

What it does: where it fits

Analyze the current Pulse Coder project/repository and turn vague or concrete needs into prioritized requirements, milestones, tasks, validation plans, and execution handoff.

Best for

  • Use when user asks “分析当前项目”, “后续需求推进”, “项目规划”, “下一步做什么”, “roadmap”, “需求拆解”, “排期”, or wants a project health check plus delivery plan.

Not for

  • Tasks that require unconfirmed production actions or broad system permissions.
  • Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

PlatformStatusEvidenceWhat to check
CodexNot declaredNo explicit evidencePortability before use
Claude CodeNot declaredNo explicit evidencePortability before use
CursorNot declaredNo explicit evidencePortability before use
Gemini CLINot declaredNo explicit evidencePortability before use
Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource
npx skills add https://github.com/hua-bang/pulse-agent --skill ".pulse-coder/skills/project-roadmap"
Safe inspection promptEditorial

Inspect the Agent Skill "project-roadmap" from https://github.com/hua-bang/pulse-agent/blob/8245c14cdee086f38128a0e4a39ccff702014ab0/.pulse-coder/skills/project-roadmap/SKILL.md at commit 8245c14cdee086f38128a0e4a39ccff702014ab0. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

  1. 01

    Required Workflow

    Identify the user’s intent:

    What is the target audience/user or business goal?What timeframe or release deadline matters?Are we planning only, or should we also implement the first slice?
  2. 02

    Phase 0 — Scope Alignment

    Identify the user’s intent:

    What is the target audience/user or business goal?What timeframe or release deadline matters?Are we planning only, or should we also implement the first slice?
  3. 03

    Phase 1 — Repository Discovery

    Run or inspect, as appropriate:

    pwd, git status --short, git branch --show-current.Workspace manifests:package.json
  4. 04

    Phase 2 — Project Map

    Produce a concise system map:

    What the product is — one paragraph.Architecture layers — runtime, tools, plugins, clients/apps, storage/integration.Key modules and ownership boundaries.
  5. 05

    Phase 3 — Health Diagnosis

    Assess the project across these dimensions:

    P0 — blocks correctness/security/release.P1 — important for near-term delivery.P2 — improves maintainability or UX.

Permission review

Static risk signals and limitations

Network access

medium · line 107

The documentation includes network, browsing, or remote request actions.

| Tool search/deferred tools | `packages/engine/src/built-in/tool-search-plugin/`, remote tool registration |

Reads files

low · line 129

The documentation asks the agent to read local files, directories, or repositories.

| “直接干” | Create execution tasks, inspect repo, implement only after scope is clear. |

Writes files

medium · line 129

The documentation asks the agent to create, modify, or delete local files.

| “直接干” | Create execution tasks, inspect repo, implement only after scope is clear. |

Reads files

low · line 327

The documentation asks the agent to read local files, directories, or repositories.

| Docs/skill-only change | parse/read file, check frontmatter has `name` and `description`; no build required unless loader changed |

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial
SignalValueEvidence typeMeaning
Quality score95/100ComputedDocumentation, specificity, maintenance, and trust rules
Repository stars28SourceRepository attention, not individual Skill quality
Compatibility0 platformsSourceDeclared in the catalog source record
Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository
hua-bang/pulse-agent
Skill path
.pulse-coder/skills/project-roadmap/SKILL.md
Commit
8245c14cdee086f38128a0e4a39ccff702014ab0
License
MIT
Collected
2026-08-25
Default branch
master
View the original SKILL.md

Project Roadmap Skill — 项目分析与需求推进

Goal

Use this skill to analyze the current project/repository and convert product or engineering needs into an actionable delivery plan.

The expected outcome is not just a summary. It must produce:

  1. Current-state project map.
  2. Evidence-backed diagnosis.
  3. Requirement clarification and decomposition.
  4. Prioritized roadmap.
  5. Milestone/task plan with validation gates.
  6. Clear next action for the agent or human team.

Trigger Examples

Use this skill when the user says things like:

  • “帮我分析当前项目,并安排后续需求推进”
  • “看一下这个项目现在该做什么”
  • “给这个需求做拆解和排期”
  • “帮我规划下一阶段 roadmap”
  • “项目体检一下,列出优先级”
  • “analyze this repo and propose next milestones”

Non-Negotiable Rules

  1. Evidence first.
    Project claims must come from files, commands, docs, tests, git history, or explicit user input. If not verified, mark as Assumption.

  2. Protect user work.
    Always inspect git status --short before proposing or making code changes. Never overwrite uncommitted user changes unless explicitly instructed.

  3. Separate planning from implementation.

    • Analysis and planning may proceed directly.
    • Code changes, deletions, migrations, production operations, and dependency updates require explicit scope clarity. If the user only asked for planning, do not implement.
  4. Ask only high-leverage questions.
    If critical information is missing, ask at most 3 focused questions. Otherwise proceed with stated assumptions.

  5. Make requirements testable.
    Every proposed requirement must include acceptance criteria or a measurable success signal.

  6. Prefer small safe increments.
    Break work into reviewable PR-sized slices. Avoid giant “rewrite everything” plans unless the repo evidence makes it unavoidable.

  7. Keep one active execution thread.
    For multi-step work, use task tracking: list/create/update tasks, keep one main task in_progress, mark blockers clearly.


Current Project Profile: Pulse Coder

When operating in this repository, treat the project as a TypeScript pnpm monorepo.

Key Workspaces

PathRole
packages/engineCore agent engine: loop, tools, context, plugins, built-in skill/task/tool-search systems.
packages/cliInteractive terminal CLI built on pulse-coder-engine.
packages/cli (src/tools/sandbox)Sandboxed JavaScript runtime backing the run_js tool.
packages/plugin-kit (src/memory)Memory integration/service module (pulse-coder-plugin-kit/memory).
packages/plugin-kitRuntime plugin toolkit, including worktree/vault/devtools helpers.
packages/acpACP client/runner integration.
packages/engine (src/orchestrator)Multi-agent orchestration module (subpath export pulse-coder-engine/orchestrator).
packages/agent-teamsMulti-session collaborative agent coordination.
packages/canvas-cliPulse Canvas CLI and bundled canvas skills.
apps/remote-serverHTTP/webhook runtime for Feishu/Discord and internal agent API.
apps/canvas-workspaceElectron canvas workbench.

Important Runtime Notes

  • Source lives in each workspace’s src/; build output goes to dist/.
  • Root commands:
    • pnpm run build
    • pnpm test
    • pnpm run dev
    • pnpm start
  • Useful targeted checks:
    • pnpm --filter pulse-coder-engine typecheck
    • pnpm --filter pulse-coder-engine test
    • pnpm --filter pulse-coder-cli test
    • pnpm --filter @pulse-coder/remote-server build
  • apps/remote-server is the webhook/server runtime. Its key files include:
    • src/index.ts
    • src/server.ts
    • src/core/dispatcher.ts
    • src/core/agent-runner.ts
    • src/core/engine-singleton.ts
    • src/routes/internal.ts
  • Skill files use .pulse-coder/skills/<skill-name>/SKILL.md with YAML frontmatter.

Common Feature Areas

Need typeStart investigation here
Agent loop behaviorpackages/engine/src/core/loop.ts, packages/engine/src/context/, packages/engine/src/ai/
Built-in toolspackages/engine/src/tools/
Plugin loading/hookspackages/engine/src/plugin/, packages/engine/src/built-in/
Skills systempackages/engine/src/built-in/skills-plugin/, .pulse-coder/skills/
Task trackingpackages/engine/src/built-in/task-tracking-plugin/
Tool search/deferred toolspackages/engine/src/built-in/tool-search-plugin/, remote tool registration
CLI UXpackages/cli/src/
Remote Discord/Feishu runtimeapps/remote-server/src/core/, apps/remote-server/src/platforms/, apps/remote-server/src/routes/
Internal scheduled runsapps/remote-server/src/routes/internal.ts, cron-related tools/routes
Memorypackages/plugin-kit/src/memory/, apps/remote-server/src/core/memory-integration.ts
Worktree/vault bindingpackages/plugin-kit/, apps/remote-server/src/core/worktree/
Canvas workbenchapps/canvas-workspace/, docs/canvas-workspace-product/, docs/06-harness-engineering-roadmap.md

Required Workflow

Phase 0 — Scope Alignment

Identify the user’s intent:

User intentDeliverable
“分析当前项目”Project map + health diagnosis + risks + immediate next steps.
“需求推进”Requirement decomposition + priority + milestone plan + task board.
“做某个功能”PRD-lite + technical plan + implementation slices + validation plan.
“排期/roadmap”Sequenced roadmap with dependencies, owners/roles, confidence, and risks.
“直接干”Create execution tasks, inspect repo, implement only after scope is clear.

If the user does not specify a target area, default to repo-wide analysis plus next 2–4 week plan.

Ask up to 3 questions only if needed:

  1. What is the target audience/user or business goal?
  2. What timeframe or release deadline matters?
  3. Are we planning only, or should we also implement the first slice?

If unanswered, continue with assumptions.


Phase 1 — Repository Discovery

Run or inspect, as appropriate:

  1. pwd, git status --short, git branch --show-current.
  2. Workspace manifests:
    • package.json
    • pnpm-workspace.yaml
    • each relevant workspace package.json
  3. Project guidance:
    • README.md, README-CN.md
    • AGENTS.md, CLAUDE.md
    • docs/, architecture/
  4. Source topology:
    • top-level packages/*/src
    • top-level apps/*/src
  5. Existing tests and scripts:
    • *.test.ts, *.spec.ts
    • package scripts
  6. Recent work context when useful:
    • git diff --stat
    • git log --oneline -10

Do not read huge generated folders such as dist/, node_modules/, release outputs, session stores, or private memory data unless directly relevant.


Phase 2 — Project Map

Produce a concise system map:

  1. What the product is — one paragraph.
  2. Architecture layers — runtime, tools, plugins, clients/apps, storage/integration.
  3. Key modules and ownership boundaries.
  4. Primary data/control flows, for example:
    • user input → platform/CLI → dispatcher/runner → engine loop → tools/plugins → response streaming
    • skill loading → registry → skill tool → detailed instructions
  5. Operational entrypoints and important commands.
  6. Known docs vs code mismatches if any.

Mark each claim as:

  • Fact — verified from repo evidence.
  • Inference — reasoned from evidence.
  • Assumption — not verified.

Phase 3 — Health Diagnosis

Assess the project across these dimensions:

DimensionCheckpoints
Product clarityWho is the user? What job-to-be-done? What is the current wedge?
ArchitectureBoundaries, dependency direction, plugin extensibility, runtime coupling.
Code qualityType strictness, duplication, naming, local complexity, generated artifacts.
TestabilityExisting tests, critical paths covered, missing integration/e2e tests.
Developer experienceBuild scripts, targeted commands, docs, setup friction.
Runtime reliabilityretries, abort, compaction, tool failure handling, state persistence.
Securitysecrets handling, internal API protection, path/file operations, webhook verification.
Observabilitylogs, run IDs, latency traces, devtools, Langfuse/plugin hooks.
Delivery riskblockers, unclear requirements, migrations, third-party APIs, platform quirks.

Use severity:

  • P0 — blocks correctness/security/release.
  • P1 — important for near-term delivery.
  • P2 — improves maintainability or UX.
  • P3 — future optimization.

Phase 4 — Requirement Intake and Decomposition

For each need, create a PRD-lite block:

## Requirement: <name>

- Problem:
- Target user / scenario:
- Desired outcome:
- Non-goals:
- Constraints:
- Acceptance criteria:
  1. ...
  2. ...
- Success metrics:
- Dependencies:
- Risks:
- Open questions:

Then decompose into engineering slices:

### Slice <N>: <small deliverable>
- Scope:
- Files likely touched:
- Implementation notes:
- Tests:
- Docs/ops updates:
- Rollback plan:
- Definition of Done:

Slices should usually fit in one focused PR/MR.


Phase 5 — Prioritization

Use a lightweight scoring model unless the user provides another one.

Score each candidate 1–5:

FactorMeaning
ImpactUser/business value if completed.
UrgencyTime sensitivity or blocking nature.
ConfidenceEvidence quality and requirement clarity.
Effort inverse5 = small/easy, 1 = large/uncertain.
Risk reductionHow much this reduces future delivery risk.

Suggested priority score:

Priority = Impact + Urgency + Confidence + EffortInverse + RiskReduction

Then classify:

  • Now / P0: must do immediately.
  • Next / P1: next milestone.
  • Later / P2: valuable but not blocking.
  • Park / P3: explicitly defer.

Also identify dependencies: “A must happen before B because …”.


Phase 6 — Roadmap and Execution Plan

Produce a roadmap at three resolutions:

  1. This week — concrete tasks, validation, expected outputs.
  2. Next 2–4 weeks — milestone sequence and dependencies.
  3. Later — strategic backlog and unknowns to resolve.

Each milestone must include:

## Milestone <name>
- Goal:
- User-visible outcome:
- Work slices:
- Validation plan:
- Release/rollback notes:
- Risks and mitigations:
- Exit criteria:

For implementation handoff, create a task plan:

| Task | Priority | Owner/Agent | Dependencies | Validation | Status |
|---|---:|---|---|---|---|

If task-tracking tools are available, create/update tasks for accepted execution work.


Phase 7 — Validation Gates

Every plan must include validation commands or checks.

For this repo, prefer targeted checks:

AreaSuggested checks
Engine loop/tools/pluginspnpm --filter pulse-coder-engine test; pnpm --filter pulse-coder-engine typecheck
CLIpnpm --filter pulse-coder-cli test; pnpm --filter pulse-coder-cli build
Sandboxpnpm --filter pulse-coder-cli test (sandbox specs live in src/tools/sandbox)
Memorypnpm --filter pulse-coder-plugin-kit test; pnpm --filter pulse-coder-plugin-kit build
Remote serverpnpm --filter @pulse-coder/remote-server build
Cross-package changepnpm run build; targeted tests first, full build last
Docs/skill-only changeparse/read file, check frontmatter has name and description; no build required unless loader changed

If validation cannot run, state why and provide the next best evidence.


Required Output Format

Use this structure by default:

# 项目分析与需求推进方案

## 1. 结论先行
- 当前判断:
- 最应该做的 3 件事:
- 最大风险:

## 2. 证据来源
| Evidence | Path/Command | What it supports | Confidence |
|---|---|---|---|

## 3. 当前项目地图
- 产品定位:
- 架构层次:
- 关键模块:
- 主要流程:

## 4. 健康诊断
| Area | Finding | Severity | Evidence | Recommendation |
|---|---|---:|---|---|

## 5. 需求拆解
<PRD-lite blocks>

## 6. 优先级排序
| Candidate | Impact | Urgency | Confidence | EffortInverse | RiskReduction | Priority | Tier |
|---|---:|---:|---:|---:|---:|---:|---|

## 7. Roadmap
### This week
### Next 2–4 weeks
### Later

## 8. 执行任务板
| Task | Priority | Dependencies | Validation | Status |
|---|---:|---|---|---|

## 9. 开放问题与决策点
- Decision needed:
- Assumption to verify:

## 10. 下一步
- Recommended immediate next action:
- If you want me to execute: <specific first slice>

Quality Checklist

Before finalizing, verify:

  • git status --short was checked or explicitly unnecessary.
  • Claims are tied to evidence or marked as assumptions.
  • Requirements have acceptance criteria.
  • Priorities explain tradeoffs, not just labels.
  • Roadmap includes dependencies and risks.
  • Execution tasks are small enough for PR-sized work.
  • Validation commands/checks are listed.
  • User work and secrets are protected.

Completion Criteria

This skill is complete when the user receives either:

  1. A repo-wide project analysis plus prioritized roadmap, or
  2. A focused requirement plan with task-level execution handoff, or
  3. A clear blocker report explaining what information is missing and the minimum questions needed to proceed.

Frequently asked questions

What to verify before installation and use

What does the project-roadmap source document cover?

Analyze the current Pulse Coder project/repository and turn vague or concrete needs into prioritized requirements, milestones, tasks, validation plans, and execution handoff.

How do I install project-roadmap?

The source record exposes this install command: npx skills add https://github.com/hua-bang/pulse-agent --skill ".pulse-coder/skills/project-roadmap". Inspect the command and pinned source before running it.

Which permission-related actions were detected?

Static rules flagged network, read-files, write-files in the source; the page lists the matching lines and excerpts.

Alternatives

Compare before choosing

Computed 10024,921

alirezarezvani/claude-skills

app-store-optimization

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist

Computed 10015,122

wanshuiyin/Auto-claude-code-research-in-sleep

citation-audit

Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.

Computed 10014,671

prowler-cloud/prowler

postgresql-indexing

PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing index usage statistics, reindexing, dropping indexes, or working with partitioned table indexes. Also trigger when discussing index strategies, partial indexes, or index maintenance

Computed 9965

brucesongs/kali-claw

insecure-design

Insecure Design (OWASP A06:2025) focuses on security flaws in system architecture and design phases, rather than code implementation-level bugs.