CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

standards-review

Review a saved standards document via a one-standard-at-a-time interview. Prompts the user for the file path, parses individual standards, then presents each one for evaluation with concrete options (Accept / Revise / Reject / Defer). Produces a summary report at the end.

Quality

84%

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

88%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-crafted, instruction-only skill body: the workflow is unambiguously sequenced, every step gives exact wording and options, and validation checkpoints (count confirmation, recap approval, verification checklist) guard the report-writing step. The only weaknesses are mild redundancy around the core constraint and a fully-inline structure that could offload the report template to a bundle file.

DimensionReasoningScore

Conciseness

The body is operational nearly everywhere (a parsing rules table, exact option sets, a copy-paste report template), but the "Mindset" section and the one-standard-per-question constraint repeated across Workflow, Anti-Patterns, and Verification are padding that could be trimmed.

4 / 5

Actionability

Guidance is fully concrete: exact question wording ("Does this recap look right? Any changes before I write the report?"), exact curated options, a specific output path pattern (`standards-review-{file-stem}-{date}.md`), and a complete report template. Per the scoring notes, absence of code is not penalized for an instruction-only skill with actionable guidance.

5 / 5

Workflow Clarity

Six clearly sequenced steps with validation at every risk point: standard-count confirmation (step 2), a recap confirmed before the report is written, a bounded feedback loop ("apply them, then re-recap once. Do not loop indefinitely"), and a final Verification checklist. The batch-operation cap does not apply since verification is explicitly present.

5 / 5

Progressive Disclosure

Well-organized single-file structure with clear ## / ### sections and easy navigation, and no nested or buried references. However, at ~143 lines (above the under-50-line simple-skill exception), the inline report template and format-parsing table are plausible candidates for a references/ or assets/ file, so the split could be slightly better.

4 / 5

Total

18

/

20

Passed

Description

71%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 strong, information-dense description that concretely enumerates the skill's workflow and its unique interview mechanics. Its main weakness is the complete absence of a "Use when..." trigger clause, which caps completeness and limits the natural trigger vocabulary to "standards" and "review".

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to review, audit, or clean up project standards or rules (e.g. RULES.md, CONTRIBUTING.md), before a migration/refactor, or after a period of drift."

Add the natural synonyms users would actually say — "audit", "rules", "guidelines", and named files like RULES.md/CONTRIBUTING.md — to broaden trigger term coverage.

Sharpen the opening so it reads as standards/rules auditing specifically (e.g. "Audit a project's standards document...") to reduce overlap with generic document-review skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full workflow — "Prompts the user for the file path, parses individual standards", "presents each one for evaluation with concrete options (Accept / Revise / Reject / Defer)", and "Produces a summary report" — with no phase of the skill left out.

5 / 5

Completeness

The "what" is clear and detailed, but there is no "Use when..." clause or equivalent explicit trigger guidance anywhere in the description. Per the judging guidelines, a missing when-clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like "standards document", "standards", and "review" are present, but common user phrasings such as "audit", "rules", or "guidelines" are missing even though the skill body itself lists them as triggers. Good coverage, a few natural synonyms absent.

4 / 5

Distinctiveness Conflict Risk

"one-standard-at-a-time interview" and "(Accept / Revise / Reject / Defer)" carve out a fairly distinct niche, but the generic opening "Review a saved standards document" leaves minor overlap risk with general document-review skills.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pantheon-org/tekhne

Path

skills/software-engineering/standards-review/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.