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

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/software-engineering/standards-review/SKILL.md

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.

The content is a strong example of an interview-process skill: fully actionable steps, exact option sets, templates, and explicit validation checkpoints with a bounded correction loop. Its only weaknesses are minor redundancy between the Workflow, Anti-Patterns, and Verification sections, and a slightly long single file whose report template could be split into a reference.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — no explanation of known concepts — but the Anti-Patterns and Verification sections partially restate constraints already stated in the Workflow ('Never bundle multiple standards or multiple questions into a single call' vs 'present exactly one question'). Matches anchor 4; not 5 due to this minor trimmable redundancy.	4 / 5
Actionability	Fully executable for an instruction-only skill: exact option labels with definitions, a parsing-rule table, exact recap question wording ('Does this recap look right?'), a copy-paste report template, and a concrete output file-naming convention with fallback paths. Matches anchor 5's 'copy-paste ready... specific examples cover the common cases'.	5 / 5
Workflow Clarity	Six clearly sequenced steps with explicit validation checkpoints: scope confirmation with a 0-count fallback, a bounded recap-confirm loop ('re-recap once. Do not loop indefinitely'), and a final verification checklist. Matches anchor 5's explicit validation steps and feedback loops; the batch-interview operation has its error-recovery paths covered.	5 / 5
Progressive Disclosure	A single SKILL.md with well-organized, clearly headed sections (Mindset, When to Use, Workflow, Anti-Patterns, Verification) and no bundle files to reference. It exceeds the 50-line simple-skill exception and the report template/recap examples could arguably live in a reference file, so anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

58%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 clearly communicates what the skill does through several concrete, named actions, but it omits any 'when to use it' trigger guidance. Adding an explicit 'Use when...' clause with natural synonyms (audit, rules, guidelines) would raise both completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the user mentions a standards review, auditing project rules, or cleaning up stale standards' — its absence currently caps completeness at 3.

Include natural synonyms and file names users would actually say (e.g. 'rules', 'guidelines', 'audit', 'RULES.md', 'CONTRIBUTING.md') to improve trigger-term coverage from 3 to 4-5.

Mention supported file formats (Markdown, plain text) in the description so the 'what' is fully comprehensive.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'Prompts the user for the file path, parses individual standards, then presents each one for evaluation with concrete options (Accept / Revise / Reject / Defer)' — with only minor gaps (no file formats or report destination). Not a 5 because coverage is not comprehensive; clearly above anchor 3's '1-2 concrete actions'.	4 / 5
Completeness	The 'what' is clear (interview-based review with named options and a summary report), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric says caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('standards document', 'review', 'standards') but common variations users would actually say — 'audit', 'rules', 'guidelines', 'RULES.md', 'CONTRIBUTING.md' — are absent (they appear only in the body, not the description). Matches anchor 3; not 4 since more than 'a few natural terms' are missing.	3 / 5
Distinctiveness Conflict Risk	The 'one-standard-at-a-time interview' over a saved standards document is a distinct niche with named options, giving it mostly distinct triggers. Not 5 because 'review' and 'standards' could overlap with general code-review or audit skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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
Commit: a1083f4

Reviewed: 3 hours ago

Table of Contents

Discovery Implementation Validation

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.