btca-local

Invoke this skill when the user says "use btca"

Quality

40%

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

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body communicates a workable single-purpose workflow with a useful startup template, but relies on custom XML-style tags instead of standard markdown (with a malformed closing tag) and stops short of giving executable git commands or validation steps. It is concise but not fully actionable or cleanly structured.

Suggestions

Replace the custom <guidelines>/<workflow>/<step> XML tags with standard markdown (numbered lists, headings) and fix the malformed second '<workflow>' tag so the structure renders correctly.

Add concrete executable commands for the load step, e.g. `git clone https://github.com/<owner>/<repo>.git ~/.btca/agent/sandbox/<repo>` and `git -C <repo> pull` for updates.

Add a verification checkpoint after clone/update (e.g. confirm the repo directory exists and is on the expected branch) before proceeding to search.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and avoids explaining concepts Claude already knows, but the Startup Cases section repeats the workflow usage three times and the opening sentence ('a simple app defined as a skill file') adds little, fitting 'mostly efficient but could be tightened' rather than the score-3 'every token earns its place' anchor.	2 / 3
Actionability	It gives concrete directions ('use ~/.btca/agent/sandbox', 'clone the main branch by default') and an output template, but provides no actual executable git commands (e.g. `git clone`, `git pull`), matching the score-2 'some concrete guidance but incomplete; missing key details' anchor rather than copy-paste-ready score 3.	2 / 3
Workflow Clarity	Steps are sequenced (work dir setup, load, search) but there are no validation checkpoints, and the custom XML-like markup is malformed (a second '<workflow>' tag opens where '</workflow>' should close), placing it at the score-2 'sequence present but checkpoints missing or implicit' anchor rather than the explicit-feedback-loop score 3.	2 / 3
Progressive Disclosure	This is a simple under-50-line skill with no bundle files, so it could score 3 on organization alone, but the non-standard XML tags instead of markdown and the broken closing tag make navigation harder, fitting the score-2 'some structure but could be better organized' anchor.	2 / 3
	Total	8 / 12 Passed

Description

30%

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 functions as a pure trigger clause with a distinctive invocation phrase but fails to convey what the skill actually does, leaving Claude unable to judge relevance from the description alone. It is concise but critically incomplete on capabilities.

Suggestions

Add a capabilities clause stating what the skill does, e.g. 'Searches git repositories cloned locally to answer questions with cited code examples.'

Broaden trigger terms beyond the single literal phrase to include natural variations like 'btca', 'search local repos', or 'better context app'.

Combine what and when into one sentence following the 'Extract text... Use when...' pattern from the good examples.

Dimension	Reasoning	Score
Specificity	The description only states the trigger ("Invoke this skill when the user says \"use btca\"") and names no concrete actions or capabilities, matching the 'vague or no actions' anchor rather than the score-2 anchor which at least names a domain and some actions.	1 / 3
Completeness	It answers 'when' (when the user says "use btca") but entirely omits 'what does this do' — no mention of searching local git repos — which is the score-1 anchor 'missing what OR when'.	1 / 3
Trigger Term Quality	The phrase "use btca" is a natural utterance a user would say, but coverage is a single literal phrase with no common variations (e.g. "btca", "search btca", "better context app"), fitting 'some relevant keywords but missing common variations' rather than the score-3 broad coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The literal trigger "use btca" is a unique token unlikely to fire for any other skill, matching the score-3 'clear niche with distinct triggers; unlikely to conflict' anchor; it is not the score-2 anchor because the trigger is distinctive rather than merely 'somewhat specific'.	3 / 3
	Total	7 / 12 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: 6d36970

Reviewed: 1 day 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.