memory-ci-capture

Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after `bm ci collect` prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for `bm ci publish`.

Quality

86%

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

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.

A lean, well-structured instruction skill that gives concrete input/output and clear synthesis rules with an integrity guardrail. The main gap is the lack of a filled worked example, which would lift actionability from solid to exemplary.

Suggestions

Add one short filled AgentSynthesis example for a sample merged PR so the empty output template becomes copy-paste ready and concrete (lifts actionability).

Make the workflow an explicit numbered sequence (read context → synthesize per rules → verify no invented evidence → return JSON) so checkpoints are explicit rather than implied (lifts workflow_clarity).

Optionally trim the two-sentence opening framing to a single line to remove the only mildly editorial touch (protects conciseness).

Dimension	Reasoning	Score
Conciseness	The body is lean and directive, assuming Claude's competence without explaining GitHub, CI, or JSON; the brief opening framing ("GitHub records the mechanics. Basic Memory remembers what changed and why.") conveys intent rather than padding concepts, so every section earns its place.	5 / 5
Actionability	Concrete, actionable guidance is given via the exact input path, a full AgentSynthesis output template, field-by-field rules, and event-specific focus areas; scored 4 rather than 5 because the output template uses empty arrays and no filled worked example illustrates the common cases.	4 / 5
Workflow Clarity	The Inputs → Output → Synthesis Rules → Event Guidance structure implies a clear sequence, and an integrity checkpoint exists ("Do not invent... If evidence is absent, say so briefly in `verification`"); scored 4 rather than 5 because the sequence is implied by section order rather than an explicit numbered flow with explicit checkpoints.	4 / 5
Progressive Disclosure	No bundle files are present and the skill is under 50 lines and single-purpose, with well-organized section headers (Inputs, Output, Synthesis Rules, Event Guidance); per the simple-skill exception this scores 5 on structure alone with no need for external references.	5 / 5
	Total	18 / 20 Passed

Description

87%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.

A precise, trigger-rich description that clearly answers both what the skill does and when to use it within a narrow, low-conflict niche. The only soft spot is specificity coverage, which lists two (very concrete) actions rather than several.

Dimension	Reasoning	Score
Specificity	"Synthesize GitHub delivery context into a concise Basic Memory project update" and "return only structured AgentSynthesis JSON for `bm ci publish`" name concrete actions tied to real CLI commands and a named JSON schema; scored 4 rather than 3 because the actions are markedly more specific than the anchor-3 example, and rather than 5 because only two actions are listed.	4 / 5
Completeness	It explicitly states both what (synthesize context into a project update and return AgentSynthesis JSON) and when ("Use in CI after `bm ci collect` prepares a ProjectUpdateContext"), matching the anchor-5 example with a concrete trigger clause; not capped at 3 because explicit trigger guidance is present.	5 / 5
Trigger Term Quality	The description includes domain-specific natural triggers a Basic Memory CI user would invoke ("bm ci collect", "bm ci publish", "ProjectUpdateContext", "AgentSynthesis JSON", "Basic Memory project update", "CI"), giving good keyword coverage with a few common variations absent.	4 / 5
Distinctiveness Conflict Risk	The Basic Memory CI niche with distinct triggers (`bm ci collect`/`bm ci publish`, `ProjectUpdateContext`, `AgentSynthesis`) is clearly distinguishable from other skills with minimal conflict risk, matching the anchor-5 clear-niche example.	5 / 5
	Total	18 / 20 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: basicmachines-co/basic-memory
Path: skills/memory-ci-capture/SKILL.md
Commit: a5fb68e

Reviewed: 3 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.