Name: decision-logger
Rating: 65.60000000000001 (1 reviews)
Author: alirezarezvani

decision-logger

Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.

Quality

79%

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 ./.gemini/skills/decision-logger/SKILL.md

The canonical home for this skill is decision-logger in alirezarezvani/claude-skills

Quality

Content

71%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 clear, actionable, and well-structured skill body with concrete commands, paths, and a checkpointed logging workflow. Its main weakness is progressive disclosure: referenced files are missing and template content is inlined.

Suggestions

Ship the referenced bundle files (scripts/decision_tracker.py and templates/decision-entry.md) so the References pointers resolve, and move the full decision-entry template block out of SKILL.md into templates/decision-entry.md.

Make the post-Phase-5 Logging Workflow steps executable by giving each step a concrete command or exact write target instead of prose like "Write Layer 1 raw transcript →".

Add a verify-the-written-record / re-validate-after-resolution checkpoint in the workflow so the conflict feedback loop (supersede/merge/defer) closes with an explicit confirmation.

Dimension	Reasoning	Score
Conciseness	The body is well-organized and largely assumes Claude's competence (command table, file paths, templates) with only minor emphatic restatements ("Never delete completed items. The history is the record.", repeated "NEVER"/"Never written by agents directly" lines) that could be trimmed.	4 / 5
Actionability	Provides concrete executable commands (python scripts/decision_tracker.py --demo/--overdue/--conflicts/...), slash-command table, exact file paths, and a full entry-format template; falls short of 5 because the post-Phase-5 workflow steps are prose descriptions ("Write Layer 1 raw transcript →") rather than literal commands.	4 / 5
Workflow Clarity	The 6-step Logging Workflow has explicit checkpoints (step 3 conflict check, step 4 surface-and-wait for founder resolution, step 6 confirm) plus a conflict-resolution feedback loop, but lacks re-validation-after-resolution guidance and a verify-the-written-record step.	4 / 5
Progressive Disclosure	The body is well-sectioned with a one-level-deep References list, but the referenced bundle files (scripts/decision_tracker.py, templates/decision-entry.md) do not exist, and a full decision-entry template plus file-structure tree are inlined rather than placed in the missing template file.	3 / 5
	Total	15 / 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 that concretely states capabilities, gives explicit multi-trigger "Use when" guidance, and carves out a distinct niche. It falls just short of perfect specificity and trigger coverage by omitting a few actions and synonyms.

Dimension	Reasoning	Score
Specificity	Names the two-layer domain and several concrete actions ("Manages raw transcripts (Layer 1) and approved decisions (Layer 2)", logging, reviewing, checking overdue), with minor gaps like conflict detection and search absent from the description.	4 / 5
Completeness	Explicitly answers both what ("Two-layer memory architecture... Manages raw transcripts... and approved decisions") and when ("Use when logging decisions after a board meeting, reviewing past decisions... or checking overdue action items") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("logging decisions after a board meeting", "reviewing past decisions", "checking overdue action items") plus slash-command triggers, but is missing common synonyms and file-extension variants that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (board-meeting decision memory) with distinct triggers (/cs:decisions, /cs:review) and an explicit auto-invocation boundary against the board-meeting skill, giving minimal conflict risk.	5 / 5
	Total	18 / 20 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
referenced_paths_exist	Referenced path issues: 7 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/decision-logger/SKILL.md
Commit: 19392f7

Reviewed: ~5 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.