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

56%

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

70%

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

A lean, well-organized simple-skill body with clear firing logic and good section structure. It could be tightened by trimming motivational prose and made more actionable by specifying how factual-assertion shapes are detected.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but the 'Why this exists' and 'What you'll see' sections explain motivation the agent largely already grasps, so it could be tightened.	2 / 3
Actionability	Provides concrete specifics (30s grounding window, 8-fire cap, skip rules, implementation path) but only describes how 'factual-assertion shape' detection works rather than specifying it, leaving a key detail implicit.	2 / 3
Workflow Clarity	For this simple single-action interceptor, the fire sequence (detect ungrounded assertion → require memory_search → integrate → send) and skip conditions are unambiguous, with no destructive operation needing validation loops.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, organized into clear sections; the single implementation path is a one-level pointer, not a nested reference chain.	3 / 3
	Total	10 / 12 Passed

Description

42%

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 specific about a single concrete action and carves out a distinct niche, but relies on technical jargon instead of natural trigger terms and omits an explicit 'Use when' clause. Adding user-facing trigger guidance would raise completeness and trigger_term_quality.

Suggestions

Add an explicit 'Use when...' clause describing the natural situations that should activate this skill.

Replace or supplement internal jargon ('factual assertion', 'grounded this turn') with terms a user would naturally say.

Optionally enumerate the concrete behaviors it performs (skip opinions/questions, 30s grounding window, fire cap) to move specificity toward 3.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('Forces a memory_search before the agent sends a message containing a factual assertion') plus a measurable outcome, but does not enumerate multiple concrete actions like a score-3 description would.	2 / 3
Completeness	Clearly states what it does, but lacks an explicit user-facing 'Use when' trigger clause — the firing condition is framed as a mechanism, so 'when' is only implied.	2 / 3
Trigger Term Quality	Uses internal mechanics jargon ('memory_search', 'factual assertion', 'grounded this turn') rather than natural keywords a user would say; no 'Use when...' phrasing.	1 / 3
Distinctiveness Conflict Risk	Targets a narrow, well-defined niche (citation-grounding before outgoing messages) tied to a specific tool, making it unlikely to conflict with unrelated skills.	3 / 3
	Total	8 / 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
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: e73c717

Reviewed: about 15 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.