flashrag-evidence

Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/flashrag-evidence/SKILL.md

Quality

Content

100%

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

The body is concise, actionable, and well-sequenced with an explicit recovery branch for low coverage, and it correctly offloads detail to a single real bundle script. It is a strong, copy-paste-ready skill body.

Dimension	Reasoning	Score
Conciseness	The body is lean and structured (When to use, Inputs, Default corpus, Workflow, Outputs, Notes) without explaining concepts Claude already knows; every section is operational. It earns score 3 over score 2 because there is no padded concept exposition — the few prose lines are necessary operational caveats.	3 / 3
Actionability	Provides fully executable commands with real flags, e.g. "python ...flashrag_evidence.py --query \"…\" --topk 8" and the bm25s variant, plus concrete output fields (path, line, score, snippet). Matches the copy-paste-ready score-3 anchor, not the pseudocode score-2 anchor.	3 / 3
Workflow Clarity	A clear 4-step sequence with an explicit recovery branch: step 4 "If coverage is low: Expand --roots ... Increase --topk ... Fallback: targeted rg -n". This feedback loop and the [Command]/[Output]/[Claim] structure satisfy the score-3 anchor; retrieval is non-destructive so no validation checkpoint is required.	3 / 3
Progressive Disclosure	Well-organized sections form a clear overview, and the one external reference — scripts/flashrag_evidence.py (verified to exist in the bundle) — is referenced one level deep and clearly signaled. Matches the score-3 anchor of a clear overview with well-signaled one-level references rather than a monolithic or nested-reference score-1/2 pattern.	3 / 3
	Total	12 / 12 Passed

Description

60%

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 states concrete capabilities but leans on domain jargon and omits an explicit "Use when..." trigger, which the body must supply. It is a competent but incomplete description.

Suggestions

Add an explicit trigger clause to the description, e.g. "Use when you need grounded, citeable evidence from local VCO/vibe docs and config (not code graphs or web facts)."

Swap jargon like "FlashRAG-style" for natural user terms ("search local docs", "citeable snippets", "find where a rule comes from") to improve trigger quality.

Briefly disambiguate from adjacent tools in the description itself (GitNexus for code graphs, web search for latest facts) to lower conflict risk.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions: "search protocols/config/skills docs and return citeable snippets with file+line anchors" — multiple specific actions (search, return citeable snippets, file+line anchors), matching the score-3 anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Answers "what" (evidence retrieval returning citeable snippets) but has no "Use when..." trigger clause in the description; the explicit "When to use" guidance lives in the body. Per the rubric, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "FlashRAG-style", "VCO/vibe", "citeable snippets" are domain jargon rather than words a user would naturally say; natural phrasings ("show me where this rule comes from") appear only in the body, not the description. Not score 1 because some relevant keywords ("evidence", "snippets") are present; not score 3 because natural-term coverage is thin.	2 / 3
Distinctiveness Conflict Risk	Scoped to "VCO/vibe" local docs/config gives it a niche, but "evidence retrieval"/"search docs" overlaps with GitNexus and web search tools that are only disambiguated in the body, not the description. Not score 3 because the description alone does not fully separate it from similar search skills.	2 / 3
	Total	9 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/flashrag-evidence/SKILL.md
Commit: f627ab5

Reviewed: about 9 hours 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.