CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ledger

Sweep the current session, repo/task context, local task files, and approved remote task stores for outstanding actionable work, then record high-confidence items in docs/outstanding-issues.md. Use when the user types /ledger or asks to extract, capture, or reconcile outstanding tasks from this session into the ledger.

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 exceptionally tight, highly actionable procedural skill: exact commands, explicit safety gates, and disciplined scope boundaries in under twenty lines. The only weaknesses are the advisory rather than mandatory validation step and a procedural reference that points outside the bundle.

DimensionReasoningScore

Conciseness

Eight lean, directive lines with zero padding and no explanation of concepts Claude already knows; even the explanatory clauses ('It creates one inbox record; a dedicated branch runs npm run issues:reconcile') convey project-specific facts that cannot be inferred. Every token earns its place.

5 / 5

Actionability

Fully executable guidance: the exact queue command with flags and placeholders ('npm run issues:add -- --pri P2 --type issue --summary "<title>" --detail "<detail>" --source "session YYYY-MM-DD /ledger sweep"'), a read-only validation command, a concrete dedupe convention ('#NNN'), and explicit gates ('Never push without an explicit ask'). Copy-paste ready.

5 / 5

Workflow Clarity

A clear numbered 1-8 sequence with most checkpoints present: dedupe against open rows, 'If nothing is new, create no request', read-only validation via 'npm run check:outstanding-issues', and a serialized current-main worktree gate for reconcile. It falls short of anchor 5 because validation is advisory ('when useful') and there is no explicit error-recovery loop if the check fails.

4 / 5

Progressive Disclosure

The body is a well-organized overview with one clearly signaled one-level-deep pointer ('Full procedure and fields: .claude/skills/ledger/SKILL.md'), matching good structure with minor gaps. It is not a 5 because the referenced path does not exist in the skill bundle (no references/ directory and the path does not resolve), leaving the promised full procedure inaccessible from the bundle itself.

4 / 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 strong description: it states concrete capabilities with a specific output artifact and gives an explicit, naturally phrased 'Use when...' trigger clause anchored on the /ledger command. The only gaps are minor — a few missing trigger synonyms and unmentioned secondary capabilities.

DimensionReasoningScore

Specificity

The description lists several concrete actions with named sources ('Sweep the current session, repo/task context, local task files, and approved remote task stores') and a specific output target ('record high-confidence items in docs/outstanding-issues.md'). It stops short of anchor 5 because it omits parts of the skill's coverage such as the reporting and dedupe steps.

4 / 5

Completeness

It clearly answers both 'what' (sweep listed sources for outstanding actionable work and record high-confidence items in a named file) and 'when' with concrete trigger phrases ('Use when the user types /ledger or asks to extract, capture, or reconcile...'). This matches the anchor-5 example structure; anchor 4 would require a less explicit 'when' clause.

5 / 5

Trigger Term Quality

'Use when the user types /ledger or asks to extract, capture, or reconcile outstanding tasks from this session into the ledger' provides good natural keywords including the explicit /ledger command. It falls short of anchor 5 because common synonyms like 'TODO', 'follow-ups', or 'pending work' are missing.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (outstanding-issues intake ledger) with distinct triggers (/ledger command, extract/capture/reconcile outstanding tasks) and minimal overlap with generic task or note-taking skills.

5 / 5

Total

18

/

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

BigSimmo/PsychSift

Path

.agents/skills/ledger/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.