Ready to supercharge your AI agents?

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

Spec Management workflow — measured AI agent skill | DecimalAI

majiayu000/agent-ops-spec

NewSkillScoreMaintained

Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.

agent-toolingby majiayu000

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Product Management pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/majiayu000-agent-ops-spec/SKILL.md

decimalai skills pull majiayu000-agent-ops-spec --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-agent-ops-spec/SKILL.md https://app.decimal.ai/s/majiayu000-agent-ops-spec/SKILL.md

Raw file: /s/majiayu000-agent-ops-spec/SKILL.md ↗ · machine-readable summary at /s/majiayu000-agent-ops-spec.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

—-50% tokens0% turns41% of whole cases pass with skill (9/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	-38%	0%
case-07	✗→✓	▲ Improved	-37%	0%
case-10	✗→✓	▲ Improved	-49%	0%
case-12	✗→✓	▲ Improved	-39%	0%
case-13	✗→✓	▲ Improved	-71%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

majiayu000 / claude-skill-registry

skills/agent/agent-ops-spec/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Spec Management workflow

Purpose

Capture, organize, and trace specifications/requirements so the agent can validate implementation against them.

Location

All specs live in .agent/specs/ with user-specified or auto-generated filenames.

Procedure

Creating a spec

1) Ask user for filename or generate one (e.g., feature-<name>.spec.md, issue-<id>.spec.md) 2) Use the spec template 3) Fill in sections from user input 4) Link spec to issue(s) in .agent/issues/ via spec_file: field

Validating against spec

1) Read the linked spec file 2) Create traceability checklist:

Each requirement → implementation location → test(s)

3) Include in critical review phase

Template

Start from spec template.

Want to see if majiayu000/agent-ops-spec would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.