signal-postmortem

Record and analyze post-trade outcomes for signals generated by edge pipeline and other skills. Track false positives, missed opportunities, and regime mismatches. Feed results back to edge-signal-aggregator weights and skill improvement backlog.

Quality

67%

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 ./skills/signal-postmortem/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 highly actionable with executable commands and concrete schemas, and it structures detail well across real reference files. Its main gap is the lack of validation/verification checkpoints in a batch feedback-generation workflow, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after recording outcomes (e.g., verify postmortem JSON against the expected schema and confirm realized returns were fetched before classifying) and after generating weight feedback.

Include a feedback loop for the batch steps: if a postmortem record fails schema validation or has a missing exit price, fix and re-record before proceeding to analysis.

Before emitting weight-adjustment suggestions, note a verification step that the min_sample_threshold (20+) and confidence gating were applied, so downstream consumers can trust the feedback.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands and concrete output schemas; minor redundancy (Overview re-derives the description and Key Principles is light padding) that could be trimmed, but no significant over-explanation of concepts Claude already knows.	4 / 5
Actionability	Fully copy-paste-ready bash commands with real flags and paths, plus concrete JSON/YAML output schemas covering the common recording and feedback cases — fully executable guidance.	5 / 5
Workflow Clarity	A clear 5-step sequence is present, but this is a batch operation (recording outcomes, generating weight-adjustment feedback for downstream skills) with no validation or verification checkpoints; per the batch/destructive guidance this caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Well-organized overview with one-level-deep references to real files (references/outcome-classification.md, references/feedback-integration.md, and two scripts) clearly listed in a Resources section; only minor organization gaps versus the ideal.	4 / 5
	Total	16 / 20 Passed

Description

58%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 clearly conveys a multi-action workflow around post-trade signal outcomes and feedback, making it specific and distinct. Its main weakness is the absence of an explicit "Use when..." trigger clause, which limits completeness and natural trigger-term coverage.

Suggestions

Append an explicit trigger clause such as "Use when reviewing closed trades or signals that have reached their holding period, or when calibrating edge-signal-aggregator weights."

Add natural trigger variations and synonyms users might say (e.g., "signal review", "trade postmortem", "outcome tracking", "signal quality audit") to broaden activation.

Keep the existing concrete action list but pair it with the "when" guidance so both what and when are explicitly answered.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Record and analyze post-trade outcomes", "Track false positives, missed opportunities, and regime mismatches", "Feed results back to edge-signal-aggregator weights and skill improvement backlog" — with only minor coverage gaps versus the comprehensive 5-anchor.	4 / 5
Completeness	Has a clear "what" but no "when" — there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain terms ("post-trade outcomes", "false positives", "missed opportunities", "regime mismatches") but lacks common natural variations/synonyms and has no explicit user-voiced trigger phrasing.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (post-trade signal outcome analysis feeding edge-signal-aggregator weights) with mostly distinct triggers; minor overlap risk with sibling signal skills keeps it just below 5.	4 / 5
	Total	14 / 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: tradermonty/claude-trading-skills
Path: skills/signal-postmortem/SKILL.md
Commit: 51c7907

Reviewed: ~6 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.