CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

screenpipe-recall

Find a past decision, document, or conversation in Screenpipe with source links.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crates/screenpipe-core/assets/skills/screenpipe-recall/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 body is an efficient, well-sequenced retrieval workflow with explicit failure handling and an appropriate one-level external reference; its only weakness is that concrete query syntax is delegated to another skill rather than shown inline.

DimensionReasoningScore

Conciseness

The body is a lean three-paragraph directive with no padding and no explanation of concepts Claude already knows (e.g., what Screenpipe is); every line earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

Concrete directives are given ('use a narrow query, then widen once if needed', 'Prefer accessibility text', 'Return the answer with timestamps and...links'), but query syntax is delegated to the screenpipe-api skill rather than shown, leaving a minor gap versus fully copy-paste guidance.

4 / 5

Workflow Clarity

A clear sequence exists (resolve time range/timezone → query narrow-then-widen → return with links) with an explicit failure checkpoint ('Report missing coverage or search failures instead of turning them into "nothing happened"'), but it stops short of the full validate→fix→retry checklist of anchor 5.

4 / 5

Progressive Disclosure

This is a sub-50-line single-purpose skill with logically organized paragraphs and a single cleanly-signaled external reference ('Read the screenpipe-api skill') with no nested references, qualifying for the simple-skills exception of 5.

5 / 5

Total

18

/

20

Passed

Description

53%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 clearly states what the skill does and ties it to a specific tool, but it lacks an explicit 'Use when...' trigger clause and broader natural synonyms, capping completeness and trigger-term quality at the midpoint.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks to find or recall a past conversation, decision, document, or meeting in Screenpipe.'

Broaden trigger terms with natural synonyms users actually say: 'search', 'recall', 'history', 'transcript', and 'meeting notes'.

Consider naming one or two additional concrete actions (e.g. 'summarize' or 'cite with timestamps') to lift specificity above a single 'Find' action.

DimensionReasoningScore

Specificity

Names the domain (Screenpipe, past decisions/documents/conversations) and one concrete action ('Find...with source links'), but does not enumerate multiple distinct actions, matching the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor at 4.

3 / 5

Completeness

The 'what' is clear (find past decisions/documents/conversations with source links) but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural phrases like 'past decision', 'document', and 'conversation' are present, but common variations users would say ('search', 'recall', 'history', 'transcript', 'meeting notes') are missing, fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Naming the specific tool 'Screenpipe' with its capture-style triggers gives a clear niche with only minor overlap risk against generic search skills, matching the 'mostly distinct; minor overlap risk' anchor rather than the fully-distinct 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

screenpipe/screenpipe

Path

crates/screenpipe-core/assets/skills/screenpipe-recall/SKILL.md

Reviewed

Table of Contents

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.