CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pi-update

Load to check the kendex Pi extensions against a Pi release, fix what breaks, and record the verdict.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 exceptionally lean, executable multi-step workflow with concrete commands, explicit validation gates, and built-in regression controls and error-recovery loops. The only structural improvement is splitting the record template and report checklist into a referenced file.

DimensionReasoningScore

Conciseness

The body is dense operational rule with no filler — e.g. "The marker `pi-extensions/pi-update.state.json` only says which releases were read" — and never explains concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: `npm view @earendil-works/pi-coding-agent@<latest|version> version dist.integrity gitHead`, the grep import-triage command, the node version-proof one-liner, and the fully flagged `npm install ... --no-save --include=dev --include=peer --include=optional --ignore-scripts`; placeholders like `<run>` and `<copy>` are explicitly defined inline.

5 / 5

Workflow Clarity

Steps 1–7 are clearly sequenced with explicit validation checkpoints and stop conditions ("The two commit values must match; a mismatch stops the run", "A version other than the target stops the run", "A check whose control passes proves nothing"), including a feedback loop that re-proves the exact merged commit in step 6 and a final `git status --short` clean check.

5 / 5

Progressive Disclosure

No bundle files exist and the single run procedure is well-sectioned (Release handling, Input, steps 1–7, Audit record, Final report, Notes), which is mostly appropriate placement; minor gap: the Audit-record/Verdict template and Final-report checklist could live in a reference file to trim the 133-line top-level body.

4 / 5

Total

19

/

20

Passed

Description

70%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 distinctive, domain-specific description with concrete actions, undermined only by the complete absence of explicit trigger guidance. Adding a when-to-use clause and a few natural synonyms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when a new Pi release lands, an extension breaks against Pi, or the user asks for a Pi compatibility check."

Include natural synonyms users would say — "compatibility check", "upgrade", "breaking changes", "changelog" — to broaden trigger-term coverage.

Optionally name the audit outputs (audit the release changelogs, prove extensions against the target SDK) to close the remaining specificity gap.

DimensionReasoningScore

Specificity

"check the kendex Pi extensions against a Pi release, fix what breaks, and record the verdict" lists several specific actions, but the audit mechanics (changelog audit, regression proof against the target SDK) are unstated — minor gaps in coverage rather than anchor 5's comprehensiveness.

4 / 5

Completeness

The description has a clear what ("check ... fix what breaks, and record the verdict") but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it is a clear what-only case, not the vague what of anchor 2.

3 / 5

Trigger Term Quality

Natural niche phrases like "Pi release", "Pi extensions" and "fix what breaks" are present, but common variations a user might actually say — "compatibility", "upgrade", "update", "breaking changes", "changelog" — are missing.

4 / 5

Distinctiveness Conflict Risk

"kendex Pi extensions against a Pi release" carves out a clear niche with distinct triggers and minimal overlap risk with any generic document- or code-handling skill.

5 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

vanillagreencom/kendex

Path

.agents/skills/pi-update/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.