CtrlK
BlogDocsLog inGet started
Tessl Logo

apm-spec-guardian

Use this skill to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-*.md), its inline / sidecar JSON Schemas (docs/src/content/docs/specs/schemas/*.schema.json), or the conformance fixture seed (tests/fixtures/spec-conformance/**). The panel fans out to four spec-ecosystem reviewers (swagger-openapi-editor, oci-distribution-editor, pkgmgr-registry-contract-editor, w3c-tag-architect), each running in its own agent thread, and a spec-editor synthesizer that produces a fold-now / defer-v0.1.1 / defer-v0.2 / reject list plus a ship decision keyed off a 1..10 shocked_meter scale. The orchestrator is the sole writer to the PR: ONE consolidated comment, no verdict labels, no merge gating. The panel is advisory -- it surfaces findings, prioritizes folds, and renders a ship recommendation that the maintainer weighs.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly sequenced orchestration skill with strong validation checkpoints and clean progressive disclosure into real bundle files. Its main weakness is redundant restatement of the advisory regime and vendor-foundation ban across sections that inflates the token budget.

Suggestions

Consolidate the advisory-regime statement: state it once in 'Architecture invariants' and reference it from the Wave sections and output contract instead of restating it verbatim each time.

Move the repeated no-vendor-foundation rule into a single canonical block (e.g. the linter or an invariant) and have Wave 3/4 prompts cite it rather than re-embedding the full token list.

Provide one copy-paste-ready example task prompt for a panelist so the orchestration is directly executable rather than described.

DimensionReasoningScore

Conciseness

Mostly efficient orchestration prose, but the advisory regime and the no-vendor-foundation rule are each restated across the intro, architecture invariants, multiple Wave sections, the output contract, and the Gotchas — redundancy that could be tightened without losing the signal.

3 / 5

Actionability

Provides concrete orchestration guidance — specific waves, exact asset/schema file paths, explicit per-task prompt requirements (PR context, severity contract, ASCII rule), and verbatim ship-decision rules — but prompts are described rather than given as copy-paste-ready blocks, leaving minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced Wave 0–6 pipeline with explicit validation checkpoints (schema-validate each panelist return, re-spawn on malformed with max attempts, validate synthesizer return, linter checklist) and feedback loops (loop-budget exhaustion escalating to the maintainer).

5 / 5

Progressive Disclosure

The body is an orchestration overview pointing one level deep to real bundle files (assets/comment-template.md, linter-checklist.md, panelist-return-schema.json, synthesizer-return-schema.json, all present) and persona agent files, with content appropriately split and clearly signaled navigation.

5 / 5

Total

17

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that explicitly covers what the skill does and when to invoke it, with a narrow activation scope that avoids conflicts. Its only minor weakness is slightly jargon-heavy trigger phrasing that omits a few natural synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'run a four-panel adversarial advisory review', 'fans out to four spec-ecosystem reviewers... each running in its own agent thread', synthesizer 'produces a fold-now / defer-v0.1.1 / defer-v0.2 / reject list plus a ship decision keyed off a 1..10 shocked_meter scale' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (four-panel fan-out + synthesizer producing fold/defer/reject lists and ship_decision) and 'when' ('Use this skill to run... on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-*.md), its inline / sidecar JSON Schemas..., or the conformance fixture seed') with concrete trigger paths.

5 / 5

Trigger Term Quality

Good keyword coverage including natural maintainer phrases ('pull request that touches the OpenAPM specification artifact', 'JSON Schemas', 'conformance fixture seed') and concrete file globs (*.md, *.schema.json, **), though a few common synonyms are absent and the language leans technical.

4 / 5

Distinctiveness Conflict Risk

Clear narrow niche — OpenAPM spec PRs touching specific path globs — with explicit scope boundaries; it even distinguishes itself from the sibling 'apm-review-panel' skill, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/apm
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.