decision

Full decision lifecycle in Semantica � record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions. Uses AgentContext, ContextGraph, DecisionQuery, CausalChainAnalyzer, DecisionRecorder.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/skills/decision/SKILL.md

Quality

Content

76%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 a concise, highly actionable command reference with strong code examples and clean sectioning, but it lacks validation/feedback steps for its write operations and has minor progressive-disclosure gaps.

Suggestions

Add a verification step after the record and exception sub-commands (e.g., query back the recorded decision_id to confirm persistence) to satisfy the validation-checkpoint expectation.

Factor the repeated `from semantica.context import AgentContext` / `ctx = AgentContext(...)` setup into a single shared preamble to trim duplicate tokens.

Consider moving the full DecisionQuery method list out of the `query` section into a references/ file with a clearly signaled link, reducing inline bulk.

Dimension	Reasoning	Score
Conciseness	Lean command reference that assumes Claude's competence and avoids explaining concepts; minor trimming possible from the repeated import/AgentContext boilerplate duplicated across all eight sub-commands.	4 / 5
Actionability	Each sub-command ships copy-paste-ready Python with real method calls, parameters, and expected output formats, fully covering the common cases.	5 / 5
Workflow Clarity	Each sub-command is clear and atomic, but the write operations (record, exception) lack any validation/verification checkpoint, so workflow clarity is capped at 3 per the batch/destructive-operations guidance.	3 / 5
Progressive Disclosure	Well-organized into eight clear per-command sections with no nested references and no bundle files; minor gaps such as the commented DecisionQuery method dump that could live in a reference file.	4 / 5
	Total	16 / 20 Passed

Description

71%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 is specific and action-rich with a clear domain niche, but it omits any explicit "when to use" trigger guidance, which caps completeness and slightly weakens trigger-term quality and distinctiveness.

Suggestions

Add a "Use when ..." clause naming concrete triggers (e.g., "Use when recording or querying decisions in Semantica, finding precedents, or analyzing decision influence").

Include natural synonyms users might say beyond the action verbs (e.g., "decision log", "decision history", "policy exceptions") to broaden trigger coverage.

Keep the named components but consider leading with the user-facing purpose before the implementation classes to improve natural trigger matching.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete lifecycle actions — "record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The "what" is clear and detailed, but there is no "Use when..." or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Good coverage of natural action verbs users would say ("find precedents", "record exceptions", "query"), but no synonyms or explicit "Use when" phrasing to round out the natural terms.	4 / 5
Distinctiveness Conflict Risk	Tied to a clear niche (Semantica decision lifecycle) with named components, making it mostly distinct; minor overlap risk because explicit trigger guidance is absent.	4 / 5
	Total	16 / 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: semantica-agi/semantica
Path: plugins/skills/decision/SKILL.md
Commit: 2a303cf

Reviewed: 1 day 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.