CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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-experiment-dev.

Quality

73%

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

Fix and improve this skill with Tessl

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

Quality

Content

71%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 skill body is a strongly actionable, well-sequenced two-phase workflow with executable commands, exact output schemas, and verification steps. Its weaknesses are duplicated content that inflates token cost and broken references to a prompts/ directory that is absent from the bundle.

Suggestions

Create the missing prompts/build_repo_acquisition_query.md and prompts/build_code_survey_query.md files (or remove the prompts/ entries from the directory tree, phase headers, and References section).

De-duplicate content shared with references/*.md (path conventions, tool mappings) and trim the closing checklists, which restate the step lists verbatim.

Add an explicit error-recovery loop for Phase A (what to do when a clone fails or all 6 cascade queries return no viable candidate) directly in the body rather than only in the referenced agent file.

DimensionReasoningScore

Conciseness

The body is operational throughout with no explanations of concepts Claude already knows, but it could be tightened: the full Phase B query template is inlined despite a dedicated prompt file being cited, the path-conventions and tool-mapping tables duplicate content in references/*.md, and the closing checklists restate the step lists.

3 / 5

Actionability

Guidance is copy-paste ready and executable: exact commands (GIT_TERMINAL_PROMPT=0 git clone --depth 1, a curl call to the GitHub API, python scripts/github_search_clone.py --query ... --limit 5 --date-limit ... with flags that match the script's actual argparse), exact JSON cache schemas, and concrete per-action command tables for the survey phase.

5 / 5

Workflow Clarity

Both phases are clearly sequenced (A1-A6, B1-B6) with an explicit validation step (A4: read README, check language/domain, reject non-matching repos) and end-of-phase checklists, matching the 4 anchor. It falls short of 5 because error-recovery feedback loops (clone failure, all cascade queries failing, API rate limits) are not stated in the body — they live only in a referenced file.

4 / 5

Progressive Disclosure

The body is well structured with clearly signaled, one-level-deep references (references/repo_acquisition_agent.md, references/code_survey_agent.md, scripts/github_search_clone.py all exist), but prompts/build_repo_acquisition_query.md and prompts/build_code_survey_query.md are cited four times and do not exist in the bundle, breaking navigation to the promised full templates.

3 / 5

Total

15

/

20

Passed

Description

63%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 specific and concrete about what the skill does and what it produces, and it is well-differentiated within its pipeline. Its main weakness is the absence of any 'when to use' trigger guidance and reliance on internal pipeline jargon rather than natural user-facing trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the selected idea lacks reference code repositories or when a concept-to-implementation code survey is needed before experiment development.'

Include natural user-facing phrases (e.g. 'find GitHub repos for the idea', 'map paper concepts to code', 'survey reference implementations') alongside the pipeline jargon.

Briefly state the 'when' context (after idea selection and resource preparation, before inno-experiment-dev) in plain language rather than only naming downstream artifacts.

DimensionReasoningScore

Specificity

Multiple concrete actions are stated ('Acquires missing code repositories', 'conducts comprehensive code survey mapping academic concepts to implementations') plus named output artifacts (acquired_code_repos, updated_prepare_res, model_survey), giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

The 'what' is clear (repo acquisition plus concept-to-code survey with named outputs), but there is no 'Use when...' clause or equivalent trigger guidance; the 'when' is only weakly implied by 'for the selected idea', which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Some relevant keywords exist ('code repositories', 'code survey', 'academic concepts', 'implementations'), but the phrasing is dominated by pipeline jargon ('Phase A', 'Phase B', 'selected idea', 'inno-experiment-dev') and lacks the natural terms or synonyms a user would actually say when needing this skill.

3 / 5

Distinctiveness Conflict Risk

Named output artifacts and the explicit pipeline position ('for downstream use by inno-experiment-dev') carve a distinct niche with clear triggers; minor overlap risk remains with generic repo-search or code-review skills.

4 / 5

Total

15

/

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

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

OpenLAIR/dr-claw

Path

skills/inno-code-survey/SKILL.md

Revision

3456bb4

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill