CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

minutes-x1-closeout

Prepare a sourced Minutes meeting outcome for human-governed closeout of existing X1 work. Use when the user wants a meeting decision or commitment to close, defer, escalate, or retire a specific X1 coordination thread. Never use it to infer settlement, move money, contact anyone, or close X1 work automatically.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is minutes-x1-closeout in silverstein/minutes

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary instruction-only skill body: a precisely sequenced, fail-closed workflow with exact tool calls, field mappings, and error-recovery handling, at high token efficiency. The single weakness is the unspecified local SHA-256 computation method in step 4.

Suggestions

Specify how to compute the two SHA-256 hashes (e.g., an exact shell command or bundled script that reads the string without a trailing newline), since ad-hoc string hashing by an LLM is error-prone.

Show one assembled `sourceProposal` JSON example (with placeholder values) so the field list has a concrete shape to copy.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no general-concept explanations, just tool calls, field mappings, and constraints (e.g., "Never send `source_meeting`, participant names, or another local Minutes path to X1"). Sentences like "Hashing the source reference minimizes it; it doesn't make the source X1-verified" are compliance rationale for non-obvious rules, not padding, so this fits the 5 anchor rather than 4's "minor instances of over-explanation".

5 / 5

Actionability

Guidance is highly concrete — named MCP tools with parameters (`get_meeting_insights` with `include_restricted: false`, `draft_coordination_closeout`) and an exact field-by-field `sourceProposal` mapping — matching the 4 anchor of concrete, executable guidance with minor gaps. The gap: `sourceRefSha256`/`sourceContentSha256` are specified only as SHA-256 "computed locally" with no method, and exact-string hashing (encoding, no trailing newline) is error-prone without an explicit command or script. Not 5 because of that missing execution detail; not 3 since everything else is directly executable.

4 / 5

Workflow Clarity

Six numbered steps with explicit validation checkpoints ("This must return `writesPerformed: false`, a bound `x1ThreadRevision`, a `proposalFingerprint`... If any is missing, stop and keep the work open") and a fail-closed section with feedback loops (stale → "Re-read both systems and prepare a new proposal"; duplicate; conflicted; oversized insight). This is the 5 anchor: clear sequence, explicit validation, error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist and none are needed: the ~90-line body is a single execution-critical workflow where the Required connections, Workflow, and Fail-closed handling sections must all be in context at run time, organized under clear headers. Per the self-contained-skill guidance this earns a 5; it is not 4 because no content is misplaced or would benefit from being split into a reference file.

5 / 5

Total

19

/

20

Passed

Description

92%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 strong description: concrete, third-person, and explicit about both capability and trigger conditions, with an unusual and valuable never-use boundary clause. The only weakness is modest synonym coverage in its trigger vocabulary.

Suggestions

Add one or two natural synonyms users might say, e.g. "resolve" or "wrap up" a thread, to broaden trigger matching without adding length.

DimensionReasoningScore

Specificity

The description enumerates concrete actions — "Prepare a sourced Minutes meeting outcome for human-governed closeout" and "close, defer, escalate, or retire a specific X1 coordination thread" — covering every disposition the workflow supports, in third-person voice. This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage); it is not 4 because coverage has no minor gaps, and not below since nothing is generic.

5 / 5

Completeness

It explicitly answers both what ("Prepare a sourced Minutes meeting outcome for human-governed closeout of existing X1 work") and when ("Use when the user wants a meeting decision or commitment to close, defer, escalate, or retire a specific X1 coordination thread"), with concrete trigger phrases plus a never-use boundary clause. This is the 5 anchor verbatim in structure, not 4, because the when-clause is fully explicit rather than improvable.

5 / 5

Trigger Term Quality

Good natural-term coverage ("meeting decision", "commitment", "close", "defer", "escalate", "retire", "X1 coordination thread"), but common synonyms a user would plausibly say — "resolve", "wrap up", "mark done" — are absent, matching the 4 anchor (a few natural terms missing). It is not 5 because no synonym variations are offered, and clearly above 3 since the core trigger vocabulary is present.

4 / 5

Distinctiveness Conflict Risk

A clear product-specific niche (Minutes MCP source × X1 coordination thread closeout) with distinct triggers and an explicit exclusion clause ("Never use it to infer settlement, move money, contact anyone, or close X1 work automatically"), giving minimal conflict risk with other skills. Not 4 — there is no realistic overlap with a closely related skill given the named systems.

5 / 5

Total

19

/

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

silverstein/minutes

Path

.opencode/skills/minutes-x1-closeout/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.