laimis91/assistant-framework/skills/assistant-skill-creator/SKILL.md
assistant-skill-creator
Create or update V1 skills and contracts. Use for skill scaffolding, contract design, or contract-compliance validation.
- Source repository stars
- 7
- Declared platforms
- 0
- Static risk flags
- 0
- Last source update
- 2026-08-04
- Source checked
- 2026-08-04
Decision brief
What it does—and where it fits
Create or update V1 skills and contracts. Use for skill scaffolding, contract design, or contract-compliance validation.
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
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
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.
npx skills add https://github.com/laimis91/assistant-framework --skill "skills/assistant-skill-creator"Inspect the Agent Skill "assistant-skill-creator" from https://github.com/laimis91/assistant-framework/blob/e85fbadd83b022d9644bbe51b11784cf2e2dfd72/skills/assistant-skill-creator/SKILL.md at commit e85fbadd83b022d9644bbe51b11784cf2e2dfd72. 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
- 01
Goal
Create compact, contract-backed V1 skills with precise routing, typed boundaries, safe fallback behavior, and offline validation.
Create compact, contract-backed V1 skills with precise routing, typed boundaries, safe fallback behavior, and offline validation. - 02
Success Criteria
The skill uses the correct Process, Analysis, or Utility contract tier.
The skill uses the correct Process, Analysis, or Utility contract tier.Root instructions state Goal, Success Criteria, Constraints, Output, and Stop Rules.Missing inputs ask only when outcome-shaping and otherwise infer, skip, or fail. - 03
Constraints
Keep root SKILL.md concise and move detail to on-demand references.
Keep root SKILL.md concise and move detail to on-demand references.Analysis and Utility skills do not gain subagent handoffs.Memory, metrics, automation, subagents, external tools, and state paths stay - 04
Progressive Contract Loading
Canonical tier files are contracts/input.yaml, contracts/output.yaml, and contracts/phase-gates.yaml.
entry for purpose, category, triggers, dependencies, policy, and existing path;currentphase for CAPTURE, DESIGN, VERIFIEDDISTILLATION, BUILD, or VALIDATE;contractdesign for ordinary contract design; - 05
Ownership
assistant-skill-creator owns skill contract design, routing precision, and contract validation. Generic workflow may coordinate file edits and review, but specialist gates are authoritative.
assistant-skill-creator owns skill contract design, routing precision, and contract validation. Generic workflow may coordinate file edits and review, but specialist gates are authoritative.
Permission review
Static risk signals and limitations
No configured static risk pattern was detected
This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.
Evidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 86/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 7 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- laimis91/assistant-framework
- Skill path
- skills/assistant-skill-creator/SKILL.md
- Commit
- e85fbadd83b022d9644bbe51b11784cf2e2dfd72
- License
- MIT
- Collected
- 2026-08-04
- Default branch
- main
View the original SKILL.md
Skill Creator
Goal
Create compact, contract-backed V1 skills with precise routing, typed boundaries, safe fallback behavior, and offline validation.
Success Criteria
- The skill uses the correct Process, Analysis, or Utility contract tier.
- Root instructions state Goal, Success Criteria, Constraints, Output, and Stop Rules.
- Missing inputs ask only when outcome-shaping and otherwise infer, skip, or fail.
- Evals cover positive routing plus a false-positive or unsafe behavior case.
Constraints
- Keep root
SKILL.mdconcise and move detail to on-demand references. - Analysis and Utility skills do not gain subagent handoffs.
- Memory, metrics, automation, subagents, external tools, and state paths stay optional/configurable and policy-gated unless the skill explicitly owns them.
- Keep examples agent-agnostic and free of secrets, private endpoints, customer data, and workplace-specific confidential details.
Progressive Contract Loading
Canonical tier files are contracts/input.yaml, contracts/output.yaml, and
contracts/phase-gates.yaml.
Read contracts/index.yaml first and load only the active boundary:
entryfor purpose, category, triggers, dependencies, policy, and existing path;current_phasefor CAPTURE, DESIGN, VERIFIED_DISTILLATION, BUILD, or VALIDATE;contract_designfor ordinary contract design;harness_designonly for loop-based Process skills;verified_distillationonly when promoting a completed workflow/lesson;validationonly for the final checklist; andcompletiononly for the artifact being returned.
Missing or invalid selectors fall back to the full named canonical contract. Do not load every contract or reference at entry.
The skill-local contract guide is generated from docs/skill-contract-design-guide.md;
edit the docs source, then run
tools/skills/sync-skill-contract-guide.sh --apply.
Ownership
assistant-skill-creator owns skill contract design, routing precision, and contract validation. Generic workflow may coordinate file edits and review, but specialist gates are authoritative.
Phases
CAPTURE
Resolve name, purpose, category, triggers, dependencies, policy constraints, and
effort. Existing skill shortcut: when existing_skill_path exists, read the
current skill and proceed to DESIGN without asking for captured facts again.
Contract tiers:
- Utility: input + output
- Analysis: input + output + phase-gates
- Process: input + output + phase-gates + handoffs
DESIGN
Load contract_design. Define typed input/output fields, recovery actions,
binary phase gates, invariants, and matching handoffs where applicable. Present
new or materially changed contract design for user review before BUILD. A small,
reversible existing-skill edit may proceed when direction is already explicit.
For a Process skill with multi-round review, QA, optimization, or restart loops,
load harness_design and apply references/harness-patterns.md: bounded rounds,
rubric/score progression, drift/stagnation handling, separate generation and
evaluation, and explicit completion/pivot artifacts.
VERIFIED_DISTILLATION
When turning a completed workflow or lesson into a reusable skill, load
verified_distillation. Require distillation_verification with
verifier_result: approved before writing. Remove task progress, PR numbers,
secrets, logs, and stale facts; otherwise return a revision checklist.
BUILD
Create skills/<name>/SKILL.md, required tier contracts, and focused evals.
Keep canonical contract headers and descriptions precise. Reuse repository
templates; add references only when they reduce root load.
VALIDATE
Load validation; run the 13 contract design guide rules plus company-safety,
source validation, eval validation, sync checks, and relevant P0-P4 contracts.
Fix failures before reporting VALIDATE COMPLETE.
Output
Return status, changed files, contract tier/summary, validation evidence, policy-safety summary, and unresolved gaps.
Stop Rules
- Stop when purpose/category ambiguity changes contract shape.
- Stop before skill work if the canonical contract guide was not read.
- Stop before BUILD when required design approval or verified distillation is absent.
- Stop before completion when contracts, evals, validation, or generated sync fail.
Alternatives
Compare before choosing
coreyhaines31/marketingskills
ab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
coreyhaines31/marketingskills
churn-prevention
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
JasonColapietro/suede-creator-skills
suede-ab-testing
Suede-owned experimentation discipline for hypotheses, sample sizing, test duration, significance, and repeatable experiment programs. Use when comparing variants, deciding whether a result is reliable, or building an experiment backlog and cadence. NOT FOR: analytics instrumentation (use suede-analytics), post-click conversion diagnosis (use suede-site-alchemy), or writing the variant copy itself (use suede-copy).
narrative-io/narrative-skills-marketplace
design-analysis
Translate a fuzzy analytical question into a rigorous investigation plan. Interrogates the ask, grounds the plan in the available data dictionary, applies analytical best practices, and produces a structured brief of query specifications for a downstream query-writing skill. Plans, does not write SQL. Use when: "why did X drop", "is there a relationship between A and B", "who are our highest-value customers", "what's driving the change in Y", "investigate this trend", "design an analysis for", "