CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-publication-safety

Use when changing PR body rendering, home-path redaction, artifact path publication, pipeline-attestation markers, or pre-push attestation.

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pr-publication-safety/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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.

The body is an exceptionally dense, zero-flush catalog of repo-specific security invariants with named functions, files, and regression tests — highly actionable for its intended maintainer audience. Its main weaknesses are run-on bullets that resist scanning and the absence of any explicit ordering or validation workflow tying the invariants together.

Suggestions

Split the longest bullets (the supplied-PR-description and update_text bullets) into labeled sub-points so each invariant is independently scannable

Add a short lead-in per section stating the order of operations (e.g., 'when touching X: check boundary in pr.go, then run the named regressions') to turn the per-bullet test names into an explicit validate-fix-retry loop

Group the regression-test names into a single 'verify' line per bullet so the validation checkpoint is visually distinct from the constraint it guards

DimensionReasoningScore

Conciseness

The body is dense with repo-specific fact and never explains concepts Claude already knows, but several bullets (notably the supplied-PR-description bullet) pack many intertwined behaviors into single run-on sentences that could be split or tightened — efficient with minor instances that could be trimmed.

4 / 5

Actionability

Guidance is concrete and executable throughout: exact ownership ('internal/safepath is the one owner'), exact constraints ('must stay free of filepath.IsAbs/VolumeName'), exact config keys ('repository_overrides.<url>.pr.update_text'), and exact commands ('axi run --pr-body-file'). Not a 5 because a few bullets describe verifier behavior (e.g., the require-no-mistakes scan) rather than direct what-to-do steps.

4 / 5

Workflow Clarity

Each change area names its regression tests, so validation checkpoints exist, but the content is a constraint catalog with no explicit sequence — the reader must synthesize what to do first, and the per-bullet checkpoints are implicit rather than an ordered workflow with feedback loops.

3 / 5

Progressive Disclosure

No bundle files exist, and the body is under 50 lines with two clear thematic headers and consistent bullet structure. However, several 200+ word bullets and the absence of any sub-structure within sections leave minor navigation gaps, fitting 'good structure; minor organization gaps' rather than fully easy navigation.

4 / 5

Total

15

/

20

Passed

Description

48%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.

The description is highly distinctive and domain-precise, but it is purely a trigger clause: it never states what the skill actually does. Adding a concrete 'what' (e.g., the invariants and redaction boundaries it documents) alongside the 'Use when' clause would materially improve it.

Suggestions

Add a 'what' clause before the 'Use when' clause, e.g., 'Enforces home-path redaction and single-attestation invariants for published PR content... Use when changing...'

Include a concrete action verb describing what the skill provides (documents boundaries, lists regression tests, states ownership rules) rather than only the single generic verb 'changing'

Add one or two natural variations of the trigger terms (e.g., 'PR body', 'attestation marker', 'evidence publication') so users phrasing the need differently still match

DimensionReasoningScore

Specificity

The description lists several specific technical surfaces ('PR body rendering, home-path redaction, artifact path publication, pipeline-attestation markers, or pre-push attestation') but the only action is the generic verb 'changing' — it names areas rather than concrete actions the skill performs, matching the anchor for naming a domain with limited actions.

3 / 5

Completeness

The 'when' is explicit ('Use when changing...') but the 'what' is never stated — the description does not say what the skill does with these changes, matching the anchor for 'only when is present without what'. Scoring only what is explicitly stated, the 'what' cannot be inferred.

2 / 5

Trigger Term Quality

Terms like 'home-path redaction', 'pre-push attestation', and 'PR body rendering' are exactly what a developer on this codebase would say, but they are single-spelling technical jargon with no synonyms or common variations, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The triggers are highly specific internal mechanisms (e.g., 'pipeline-attestation markers', 'pre-push attestation') that no other skill would plausibly claim, giving a clear niche with minimal conflict risk.

5 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

kunchenguid/no-mistakes

Path

.agents/skills/pr-publication-safety/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.