Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Recipe Update Doc · shinpr | DecimalAI

documentationby shinpr

Recipe Update Doc

shinpr/recipe-update-doc

Source shinpr/claude-code-workflows ↗License MIT

Update existing design documents (Design Doc / PRD / ADR) with review

SkillScore41Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Doc Ops pack

Last verified 8/18/2026

What it changes

Passed 5 of 11 test cases with the skill, and 2 of 11 without it.

Without skill18%

With skill41%

Checks it passed that the model alone missed

Excludes design-sync during PRD review.
Excludes code-verifier during PRD review.
Logs the failure, presents the error to the user, and retries the subagent invocation once.

and 5 more in the full report

7 fixed2 passed either way11 still failing2 broke

Pass-rate lift: +23 pp
Tokens: +83%
Agent turns: 0%
Response time: -36%

Model gemini-3.6-flashMeasured 8/18/2026v29 of 22 cases passed with skill · 11 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/shinpr-recipe-update-doc/SKILL.md https://app.decimal.ai/s/shinpr-recipe-update-doc/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add shinpr-recipe-update-doc, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/shinpr-recipe-update-doc/ and pins it in .decimal/skills.lock

decimalai skills add shinpr-recipe-update-doc

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/shinpr-recipe-update-doc/SKILL.md https://app.decimal.ai/s/shinpr-recipe-update-doc/SKILL.md

Raw file: /s/shinpr-recipe-update-doc/SKILL.md ↗ · machine-readable summary at /s/shinpr-recipe-update-doc.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

After updating `docs/design/cache.md`, what verification step must occur on the document diff before requesting user approval?

What was checked, without and with the skill
Checked	Without skill	With skill
Maps every diff hunk to an approved item or required consistency update before requesting final approval.	Missed	Passed

case-20 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md194 linessingle file

Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.

Context: Dedicated to updating existing design documents.

Orchestrator Definition

Core Identity: "I am an orchestrator." (see subagents-orchestration-guide skill)

Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.

Review Resolution Gate [MANDATORY]: Resolve every actionable deliverable-review finding through subagents-orchestration-guide Review Resolution before correction or progression. Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.

First Action: Register Steps 1-6 using TaskCreate before any execution.

Execution Protocol:

Invoke named specialists for deliverable production — pass deliverable paths between them and validate their results (see subagents-orchestration-guide "Orchestrator Execution Boundary")
Execute update flow:
- Identify target → Clarify changes → Update document → Review → Consistency check
- Stop at the [Stop: Final approval] marker → Wait for user approval before completing
Scope: Complete when updated document receives approval

At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.

CRITICAL: Execute document-reviewer — it is the quality gate for document accuracy.

Workflow Overview

Target document → change clarification
                        ↓
              technical-designer / technical-designer-frontend / prd-creator (update mode)
                        ↓ (Design Doc only)
              code-verifier → document-reviewer
                        ↓ (Design Doc only)
              design-sync → [Stop: Final approval]

Scope Boundaries

Track record

Benchmark

5 / 11

test cases passed, vs 2 / 11 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

shinpr / claude-code-workflows

skills/recipe-update-doc/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.