CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sync-agent-infra

Reconcile contributor skills, AGENTS.md, CONTRIBUTING.md, issue and PR templates, and workflow references after repository workflow changes.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An efficient, well-structured instruction-only skill: a concrete maintenance map, a sequenced consistency checklist with a genuine fix-and-recheck loop, and a verification command. The only weaknesses are minor — a restated policy in step 5 that duplicates CONTRIBUTING.md, and fix guidance that stays at the "fix contradictions" level of abstraction.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — the maintenance map table and checklists carry no padding and no explanation of general concepts — but step 5 restates the full PR-close exception policy ("except automated dependency updates and build or flaky-test fixes from authors with write access") before pointing to "as described in CONTRIBUTING.md", a minor duplication that could be trimmed to anchor 4 rather than 5.

4 / 5

Actionability

Guidance is concrete throughout: named files and skills per change type in the maintenance map, specific comparison targets in each numbered check, and the executable command "npx -y skills add . --list" run from a disposable clean copy. The gaps keeping it below anchor 5 are that remediation is left as the bare "Fix contradictions" and criteria like checking "for stale workflow statements" require judgment without examples.

4 / 5

Workflow Clarity

The process has a clear trigger section ("When to run"), an eight-step numbered checklist, an explicit feedback loop ("Fix contradictions, then repeat the affected checks"), a verification command in step 8, and a closing reporting requirement ("Report files changed and any remaining drift") — matching the anchor 5 pattern of explicit validation and error-recovery loops.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist), and its four well-organized sections plus one-level, clearly signaled links into repo docs (e.g., the Label Discovery anchor in CONTRIBUTING.md) satisfy the simple-skill exception for a top progressive-disclosure score.

5 / 5

Total

18

/

20

Passed

Description

78%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 precise, appropriately terse description that names its artifacts concretely and includes an explicit temporal trigger. Its main limitations are the single action verb and a broad when-clause that could enumerate the specific triggering changes. Third-person voice is used correctly and there is no fluff.

Suggestions

Add one or two more concrete action verbs (e.g., "...and fix inconsistencies between them") to lift specificity toward comprehensive coverage.

Enumerate the triggering changes in the description itself (e.g., "Use after adding, removing, or renaming skills, or changing issue/PR conventions") to make the when-clause more explicit and improve trigger-term coverage.

Include a natural synonym such as "sync" or "stale cross references" so users phrasing the need differently still match the skill.

DimensionReasoningScore

Specificity

The description enumerates five concrete artifact types ("contributor skills, AGENTS.md, CONTRIBUTING.md, issue and PR templates, and workflow references") but relies on a single action verb ("Reconcile") without companion actions such as checking or fixing, so it matches anchor 4 rather than the comprehensive multi-action anchor 5 or the domain-only anchor 3.

4 / 5

Completeness

Both "what" (reconcile the named artifacts) and "when" ("after repository workflow changes") are explicitly stated, so the missing-trigger cap at 3 does not apply, but the when-clause is a single broad condition rather than the concrete enumerated triggers (adding/removing skills, changing templates) the body details — anchor 4.

4 / 5

Trigger Term Quality

"AGENTS.md", "CONTRIBUTING.md", "issue and PR templates", and "repository workflow changes" are phrases a maintainer would naturally say, giving good keyword coverage, though common variations like "sync", "stale references", or "out of date" are missing — anchor 4, not the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — contributor-infrastructure consistency across specifically named files — and the other skills it touches (create-github-pr, update-docs-from-commits) are its subjects rather than competitors, giving minimal conflict risk per anchor 5.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 3 suspicious

Warning

Total

13

/

16

Passed

Repository

NVIDIA/OpenShell

Path

.agents/skills/sync-agent-infra/SKILL.md

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.