CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

grep

Search file contents using regex pattern across directories. Cross-platform pure Python implementation (no external tools needed). Returns matching lines with file paths and line numbers.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/system/grep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary minimal tool-reference document: a complete parameter table with defaults, three executable JSON examples covering common usage, and brief operational notes, with zero padding. Nothing is missing for a skill of this scope, and nothing should be moved to separate files.

DimensionReasoningScore

Conciseness

The body is a lean parameter table, three minimal JSON examples, and short notes — no explanations of concepts Claude already knows and no padding. Every token earns its place, matching the 'lean and efficient' anchor.

5 / 5

Actionability

The three JSON examples are complete, copy-paste-ready invocations covering the common cases (function search, case-insensitive TODO search, contextual search), the parameter table specifies types and defaults, and the notes document the return format ('file:line_number:content'). This matches 'fully executable; copy-paste ready; specific examples cover the common cases'.

5 / 5

Workflow Clarity

This is a simple, single-purpose, read-only skill with an unambiguous single action (invoke with pattern and optional filters), which the rubric's simple-skill exception allows to score 5 without a multi-step workflow. The destructive/batch cap does not apply since searching is non-destructive.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the rubric explicitly allows a 5 in that case with well-organized sections. Sections (Parameters, Examples, Notes, Related Skills) are clearly headed, no content that belongs in separate files is inlined, and there are no bundle files or nested references to break navigation.

5 / 5

Total

20

/

20

Passed

Description

53%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 answers 'what' concretely and occupies a distinct niche, but lacks any 'when to use' trigger guidance and misses natural synonyms like 'grep' or 'find text'. It reads like a tool capability summary rather than a trigger-optimized skill description. Adding a 'Use when...' clause with natural trigger phrases would lift completeness and trigger-term quality simultaneously.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to grep, search, or find text/patterns in files or codebases.'

Include natural synonyms and phrasings users actually say — 'grep', 'find in files', 'search code' — to broaden trigger-term coverage.

Optionally enumerate one or two more concrete capabilities (e.g., case-insensitive matching, filename glob filtering, context lines) to strengthen specificity.

DimensionReasoningScore

Specificity

The description names the domain ('Search file contents using regex pattern across directories') and two concrete behaviors ('Returns matching lines with file paths and line numbers'), matching the 'names domain and 1-2 concrete actions' anchor. It falls short of 4 because it does not enumerate several distinct actions (e.g., filtering by glob, case-insensitive matching, context lines).

3 / 5

Completeness

The 'what' is clearly answered (regex content search returning file:line matches), but there is no 'Use when...' or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 without an explicit, even if imperfect, 'when' clause.

3 / 5

Trigger Term Quality

Relevant keywords like 'search', 'file contents', 'regex', and 'matching lines' are present, but common natural variations users would say — 'grep', 'find text in files', 'search code' — are missing. This sits at 'some relevant keywords but missing common variations', below the 'good keyword coverage' anchor at 4.

3 / 5

Distinctiveness Conflict Risk

Regex-based file-content search is a recognizable niche (grep territory) with distinct triggers, so it is 'mostly distinct' rather than 'somewhat specific' (3). It falls short of 5 because the description does not explicitly distinguish it from adjacent filename/file-lookup skills, leaving minor overlap risk.

4 / 5

Total

13

/

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

openakita/openakita

Path

skills/system/grep/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.