DE

deliverable-selfloop

Runs pass/fail quality gates on completed deliverables.

Install

mkdir -p .claude/skills/deliverable-selfloop && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13009" && unzip -o skill.zip -d .claude/skills/deliverable-selfloop && rm skill.zip

Installs to .claude/skills/deliverable-selfloop

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when a reader-facing deliverable exists and needs a deterministic PASS/FAIL quality gate. **Trigger**: self loop, self-loop, polish deliverable, quality gate, fix-on-fail, 收敛, 自循环, 质量门. **Use when**: A pipeline has produced a reader-facing deliverable (`output/*.md`) and you want deterministic convergence to PASS. **Skip if**: You are still pre-approval for prose or the upstream evidence/structure artifacts are missing. **Network**: none. **Guardrail**: Do not invent papers/citations/results. Only use in-scope inputs already present in the workspace.
560 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Evaluate reader-facing deliverables against a contract
  • Generate a PASS/FAIL report for deliverable quality
  • Detect the active deliverable contract
  • Run matching evaluator for the deliverable
  • Check for minimum section and artifact contract satisfaction

How it works

The skill detects the deliverable contract, runs a matching evaluator, and then writes a PASS/FAIL report based on predefined acceptance criteria.

Inputs & outputs

You give it
A reader-facing deliverable like `output/*.md`
You get back
`output/DELIVERABLE_SELFLOOP_TODO.md` and a scorecard (e.g., `output/BRIEF_SCORECARD.md`)

When to use deliverable-selfloop

  • Verifying deliverable quality
  • Checking paper reviews
  • Validating research briefs
  • Enforcing quality gates

About this skill

Deliverable Self-Loop

Runs the final quality gate for a reader-facing deliverable and always writes a PASS/FAIL report.

Inputs

Primary input depends on the active pipeline contract:

  • brief deliverable
  • paper-review deliverable
  • evidence-review deliverable
  • idea memo bundle
  • tutorial deliverable

Output

  • output/DELIVERABLE_SELFLOOP_TODO.md
  • for research-brief: output/BRIEF_SCORECARD.md and output/BRIEF_SCORECARD.json
  • for paper-review: output/REVIEW_SCORECARD.md and output/REVIEW_SCORECARD.json
  • for idea-brainstorm: output/IDEA_SCORECARD.md and output/IDEA_SCORECARD.json
  • for evidence-review: output/EVIDENCE_SCORECARD.md and output/EVIDENCE_SCORECARD.json

Dispatch rule

The gate should dispatch by pipeline contract first:

  • quality_contract.deliverable_kind

Only fall back to legacy profile-name checks when contract metadata is missing.

Script boundary

scripts/run.py should:

  • detect the active deliverable contract
  • run the matching evaluator
  • always write a report

It should not mutate the deliverable itself.

Acceptance

  • report exists
  • report contains - Status: PASS or - Status: FAIL
  • PASS only when the active deliverable satisfies its minimum section / artifact contract
  • research-brief additionally requires valid core-set pointers and the configured score threshold
  • paper-review additionally requires the configured score threshold and all critical rubric dimensions
  • idea-brainstorm additionally requires traceable anchors, actionable lead directions, and the configured score threshold
  • evidence-review additionally requires clause-linked screening, complete extraction rows, synthesis pointers, and the configured score threshold

Non-goals

  • rewriting the deliverable
  • choosing upstream fixes beyond pointing to the missing contract items

When not to use it

  • When prose is still pre-approval
  • When upstream evidence or structure artifacts are missing

Limitations

  • Does not mutate the deliverable itself
  • Does not rewrite the deliverable
  • Does not choose upstream fixes beyond pointing to missing contract items

How it compares

This skill provides an automated, deterministic quality gate for deliverables, contrasting with manual review processes.

Compared to similar skills

deliverable-selfloop side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
deliverable-selfloop (this skill)03moReviewIntermediate
wrap07moReviewIntermediate
session-wrap17moReviewIntermediate
windsurf-custom-prompts12moNo flagsBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry