btca-local

Invoke this skill when the user says "use btca"

Quality

35%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/btca-local/SKILL.md

Quality

Content

36%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 conveys a recognizable workflow and startup behavior but gives almost no executable guidance for its core search action, lacks any validation for its batch/destructive repo operations, and uses malformed custom XML tags instead of standard markdown. It is concise but not actionable enough to reliably execute.

Suggestions

Add concrete, copy-paste-ready commands for each step (e.g. 'git clone <url> ~/.btca/agent/sandbox/<name>', 'git -C <path> pull', and a grep/ripgrep example for searching).

Replace the custom <guidelines>/<workflow>/<step> XML tags with standard markdown (bulleted guidelines, numbered steps) and fix the malformed closing '</workflow>' tag on line 40.

Insert a validation/checkpoint step after loading and after searching (e.g. confirm the clone succeeded and that citations map to real files before answering), since cloning/updating/cleaning repos are batch/destructive operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not explain concepts Claude already knows, but it contains filler ('this one's simple, simply answer...') and overlapping repetition across the three startup cases that could be tightened; not score 4 due to these padding instances.	3 / 5
Actionability	Core steps are high-level hints ('clone them', 'search the repo for the information you need') with no executable git/grep commands, and despite the skill's own guideline demanding 'complete code snippets' it provides none, fitting 'minimal concrete guidance; missing the specific steps to execute'.	2 / 5
Workflow Clarity	A rough sequence exists (setup → load → search) but steps are poorly defined, validation is absent, and the '<workflow>' tag on line 40 is malformed (should be '</workflow>'); the destructive/batch repo-update/cleanup operations with no validation cap this at 3, and the vague steps pull it to 2.	2 / 5
Progressive Disclosure	Content is sectioned into workflow and startup cases with no external references needed, but it relies on non-standard custom XML tags instead of markdown and contains a broken nesting tag, so structure is present but could be better organized; not score 4 due to the malformed/atypical structure.	3 / 5
	Total	10 / 20 Passed

Description

35%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 essentially a bare trigger clause with no statement of what the skill does, leaving capability and context entirely unspecified. Its only strength is a distinctive literal invocation phrase.

Suggestions

Add a 'what' clause naming the skill's concrete actions, e.g. 'Searches git repos cloned locally and answers questions using their contents.'

Expand trigger coverage beyond the single exact phrase to natural variants like 'search a local git repo' or 'use btca to look up code'.

Combine what and when in one sentence, e.g. 'Searches locally cloned git repos to answer questions with citations. Use when the user says "use btca" or asks to search a local repo.'

Dimension	Reasoning	Score
Specificity	The description ('Invoke this skill when the user says "use btca"') names no capabilities or concrete actions whatsoever — it is a pure trigger with zero 'what' detail, matching the 'entirely vague; no concrete actions' anchor.	1 / 5
Completeness	Only the 'when' is present ('when the user says "use btca"') with no 'what does this do' at all, which matches the anchor 'only when is present without what'; not score 3 because no capability is even weakly implied.	2 / 5
Trigger Term Quality	It includes a single concrete trigger phrase ('use btca') that a user would actually say, but offers no synonyms, variations, or domain keywords, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The literal exact phrase trigger ('use btca') is highly distinctive with minimal overlap risk, but with no capability niche described it does not reach the comprehensive 'clear niche with distinct triggers' level of 5.	4 / 5
	Total	10 / 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: stickerdaniel/linkedin-mcp-server
Path: .agents/skills/btca-local/SKILL.md
Commit: 0cd1e5f

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.