inno-code-survey

Acquires missing code repositories for the selected idea (Phase A) and conducts comprehensive code survey mapping academic concepts to implementations (Phase B). Outputs acquired_code_repos, updated_prepare_res, and model_survey for downstream use by inno-implementation-plan.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/inno-code-survey/SKILL.md

Quality

Content

76%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 highly actionable and well-sequenced with explicit validation checkpoints and a real helper script. Its weaknesses are mild verbosity from inlined templates/schemas and a progressive-disclosure gap where the referenced prompt files are missing from the bundle.

Suggestions

Create the referenced prompts/build_repo_acquisition_query.md and prompts/build_code_survey_query.md files, or remove those citations, since the bundle currently lacks a prompts/ directory.

Move the inlined Phase B query template and the large cache JSON skeletons into the reference/prompt files they point to, keeping SKILL.md as a lean overview.

Trim the duplicated checklist and 'Tool mappings' table where they restate steps already covered in the phase sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands and tight tables, but the inlined query template, full cache JSON skeletons, and duplicated checklists add length that could be trimmed without losing value.	3 / 5
Actionability	Fully executable guidance throughout: copy-paste bash/git/curl commands, a real helper script with documented flags, JSON output schemas, and a concrete command table for repo navigation.	5 / 5
Workflow Clarity	Clearly sequenced two-phase workflow (A1-A6, B1-B6) with explicit verification checkpoints (A4 verify each clone), reject criteria, and a closing checklist; the clone/search/verify loop is a proper feedback checkpoint.	5 / 5
Progressive Disclosure	Body references one-level-deep files (references/repo_acquisition_agent.md, code_survey_agent.md, scripts/github_search_clone.py) that exist, but the cited prompts/build_*.md files do not exist in the bundle, and large query templates and JSON skeletons are inlined rather than externalized.	3 / 5
	Total	16 / 20 Passed

Description

57%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 conveys the two-phase purpose and concrete outputs but omits an explicit 'Use when...' trigger, which caps completeness. Trigger terms are domain-appropriate but miss common natural phrasings.

Suggestions

Add an explicit 'Use when...' trigger clause naming the conditions that should activate this skill (e.g., 'Use when an idea has been selected and missing technical components must be found and surveyed before implementation').

Add natural user-facing keywords/synonyms such as 'GitHub repos', 'map concepts to code', or 'find reference implementations'.

Tighten the pipeline-jargon outputs ('acquired_code_repos', 'updated_prepare_res', 'model_survey') or move them after the trigger clause so the user-facing value comes first.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions ('Acquires missing code repositories', 'conducts comprehensive code survey mapping academic concepts to implementations'), with minor coverage gaps around the exact survey/report outputs.	4 / 5
Completeness	Clearly answers 'what' (two-phase acquisition + survey with named outputs) but provides no explicit 'when/Use when' trigger clause, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Contains some relevant terms ('code survey', 'academic concepts to implementations', 'code repositories') but lacks the natural phrasings a user would say and missing synonyms like 'GitHub repos' or 'map concepts to code'.	3 / 5
Distinctiveness Conflict Risk	The 'academic concepts to implementations mapping' niche is fairly distinct from generic repo skills, with only minor overlap risk against related code-exploration skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/inno-code-survey/SKILL.md
Commit: 4b35756

Reviewed: 5 days 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.