recall-before-claim

Forces a memory_search before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from ~40% to ~90%+.

Quality

65%

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 ./skills/recall-before-claim/SKILL.md

Quality

Content

85%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 content is concise, well-structured, and actionable for a simple single-purpose interceptor skill. It provides concrete implementation pointers and clear firing/non-firing conditions without over-explaining.

Dimension	Reasoning	Score
Conciseness	The body is lean with well-organized sections where each section earns its tokens; minor narrative padding in 'Why this exists' keeps it just below a perfect 5.	4 / 5
Actionability	Concrete details are provided—interceptor id, file path, intervention type, activation condition, and rate limit—giving a maintainer exact pointers, though no executable code snippet is included.	4 / 5
Workflow Clarity	As a single-purpose skill with an unambiguous flow (detect assertion → check prior memory tool → require memory_search) and explicit non-firing conditions, it meets the simple-skill exception for a top score.	5 / 5
Progressive Disclosure	Under 50 lines with no external references and clearly organized sections, satisfying the rubric's simple-skill exception for progressive disclosure.	5 / 5
	Total	18 / 20 Passed

Description

46%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 states a clear, specific capability but lacks an explicit 'Use when' trigger clause and leans on technical jargon rather than natural user keywords. Distinctiveness is good despite the missing trigger phrasing.

Suggestions

Add an explicit 'Use when…' clause naming natural user contexts (e.g., 'Use when the agent is about to make a factual claim it has not grounded against memory this turn').

Replace or supplement jargon ('grounded', 'citation-rate gap') with natural trigger terms users and reviewers would actually say.

Broaden specificity by listing the memory tools consulted (memory_search / deep_recall / knowledge_graph_search) directly in the description.

Dimension	Reasoning	Score
Specificity	Names one concrete action ('Forces a memory_search') tied to a concrete trigger ('factual assertion that has not yet been grounded'), but offers only a single action rather than several specific actions.	3 / 5
Completeness	It clearly states what the skill does, but provides no explicit 'Use when…' or trigger guidance for when to apply it, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Terms like 'memory_search', 'factual assertion', and 'grounded' are system jargon rather than the natural phrases a user would say; common natural variations and synonyms are missing.	2 / 5
Distinctiveness Conflict Risk	The interceptor targets a specific niche (ungrounded outgoing assertions) with low overlap risk; only minor overlap with general recall skills and no distinct natural trigger phrases keep it just below 5.	4 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/recall-before-claim/SKILL.md
Commit: 017761f

Reviewed: 2 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.