AGENT SKILL

evidence-gate

Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

License 许可
MIT
所属仓库
marcioaltoe/skills
最近更新
2026-11-14
Stars
★ 0
Forks
2

01 前言 Front Matter

name
evidence-gate
version
0.0.2
metadata
{ "tags": [ "qa", "testing", "code-review", "workflow" ], "author": "Marcio Altoé", "source": "https://github.com/marcioaltoe/skills", "version": "0.0.2", "category": "qa" }
description
Require fresh verification evidence before claiming work is complete, fixed, passing, committed, PR-ready, or ready for handoff. Use before completion claims, commits, pushes, PR creation, issue status changes, delivery summaries, or agent handoffs; do not use for brainstorming or planning that makes no delivery claim.

03 SKILL.md 正文

Evidence Gate

Evidence comes before status. Do not say work is complete, fixed, passing, ready, committed, pushed, PR-ready, or handoff-ready until the current turn includes evidence for that exact claim.

When to use

  • Before saying a task is done or fixed
  • Before committing or pushing
  • Before opening or updating a PR
  • Before marking an issue ready for review or done
  • Before handing work to another agent or human
  • After an agent, tool, or CI job reports success

Gate

  1. State the claim you are about to make.
  2. Identify the smallest command or inspection that proves that claim.
  3. Run the full command, or inspect the required artifact.
  4. Read the output and exit code.
  5. Compare the result to the claim.
  6. Report the exact evidence, or state the blocker.

Evidence matrix

Claim Evidence required
Tests pass Test command exits 0 and reports no failures
Lint clean Lint command exits 0 and reports no warnings
Typecheck/build passes Typecheck/build command exits 0
Bug fixed Original reproduction or regression check passes
Requirements met Checklist against requested scope, not tests alone
Commit ready git diff --cached reviewed plus relevant checks
Push ready Branch, commit, and remote target verified
PR ready Verification commands, PR title/body, diff scope
Handoff ready Current status, changed files, verification result

Reporting format

Use this structure in the final response or handoff:

Verification:
- `<command>`: passed
- `<command>`: failed — <reason>

Not run:
- `<command>` — <reason>

If a check fails, do not soften the result. State the failure and the next action.

Anti-patterns

  • Saying "should pass" without running the check.
  • Treating one passing check as proof of all checks.
  • Trusting a tool or subagent success message without inspecting the diff or output.
  • Opening a PR with missing local verification notes.
  • Marking scope complete because tests pass.

04 同仓库更多 Skills

marcioaltoe
marcioaltoe/skills

startup-validator

Comprehensive startup idea validation and market analysis tool. Use when users need to evaluate a startup idea, assess market fit, analyze competition, validate problem-solution fit, or determine market positioning. Triggers include requests to "validate my startup idea", "analyze market opportunity", "check if there's demand for", "research competition for", "evaluate business idea", or "see if my idea is viable". Provides data-driven analysis using web search, market frameworks, competitive research, and positioning recommendations.

★ 0
marcioaltoe
marcioaltoe/skills

positioning-icp

When the user wants to define their ideal customer profile, position an AI product, build messaging architecture, or validate product-market fit. Also use when the user mentions 'ICP,' 'ideal customer profile,' 'positioning,' 'PMF,' 'product-market fit,' 'messaging,' 'buyer persona,' 'enrichment signals,' 'market positioning,' or 'competitive positioning.' This skill covers market positioning, ICP definition, messaging architecture, and PMF validation for AI-native products. Do NOT use for technical implementation, code review, or software architecture.

★ 0
marcioaltoe
marcioaltoe/skills

copywriting

When the user wants to write or rewrite page copy (homepage, landing, pricing, feature), or asks which headline, promise, or message to lead with. Diagnoses the input first (blank brief, real voice, or point edit) and changes only what it calls for. Claims must be supportable; a declined claim names the evidence that would unlock it. No AI tells like 'it's not X, it's Y' or 'no X, no Y, no Z'. For editing, see copy-editing. For emails, see emails. For the offer, see offers.

★ 0
marcioaltoe
marcioaltoe/skills

business-storyteller

Transforms technical work into persuasive business-language documents for non-technical stakeholders, including internal announcements, approval proposals, incident explainers, technical-debt cases, product explainers, and investor or partner memos. Use when the user asks to present technical work to the company, explain software to business teams, write a business case, make an approval document, or convert a technical artifact into stakeholder communication in the requested language. Do not use for READMEs, specs, ADRs, external marketing pages, or customer-facing sales copy.

★ 0
marcioaltoe
marcioaltoe/skills

brand-storytelling

Help users craft compelling brand narratives. Use when someone is defining brand strategy, writing company positioning, creating pitch narratives, developing messaging frameworks, or trying to make their company story more memorable.

★ 0
marcioaltoe
marcioaltoe/skills

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

★ 0