continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Use when capturing lessons from a session, managing instincts, or promoting them into skills, commands, or agents.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/continuous-learning-v2/SKILL.md

Quality

Content

63%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 actionable and the end-to-end workflow is well sequenced with a dry-run checkpoint on the main batch operation, but it is verbose for its length — duplicating the command list and carrying two historical comparison tables — and keeps reference material inline rather than progressively disclosing it to bundle files.

Suggestions

Remove the duplicate command listing: keep either the Quick Start commented examples or the Commands table, not both.

Collapse the two "What's New" version tables into a single concise changelog or move them to a references/CHANGELOG.md and link to it.

Add a short "Bundle files" / references section that one-level-deep links to scripts/instinct-cli.py, scripts/migrate-homunculus.sh, and the observe.sh hook instead of burying those paths in prose.

Dimension	Reasoning	Score
Conciseness	The ~370-line body is mostly efficient but carries padded sections: two historical version-comparison tables (v2.1 vs v2.0 and v2 vs v1), the instinct commands listed twice (Quick Start comments and the Commands table), and a "Why Hooks vs Skills" rationale section that explains concepts rather than instructs.	3 / 5
Actionability	Concrete, executable guidance is provided throughout — slash commands with usage, a settings.json hook block, mkdir setup, and `python3 instinct-cli.py promote [--dry-run]` invocations — with only minor gaps (the instinct-cli.py subcommand surface is not exhaustively enumerated).	4 / 5
Workflow Clarity	The "How It Works" diagram and numbered Quick Start sequence the multi-stage pipeline clearly, and the destructive/batch promote operation has a `--dry-run` validation checkpoint; a couple of operations (e.g. the one-time migrate script) lack an explicit post-run verify step, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Section structure is reasonable, but reference-style content (two version tables, the scope-decision guide, confidence-scoring reference) is inlined in SKILL.md rather than split out, and pointers to the real bundle scripts (instinct-cli.py, migrate-homunculus.sh, observe.sh) are embedded in prose instead of a clearly signaled one-level-deep reference section.	3 / 5
	Total	14 / 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.

The description is strong: it states concrete capabilities in third person and closes with an explicit 'Use when' clause covering multiple natural triggers. Minor headroom remains only on trigger-term synonym coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "observes sessions via hooks", "creates atomic instincts with confidence scoring", "evolves them into skills/commands/agents", plus "project-scoped instincts to prevent cross-project contamination" — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (observes sessions, creates atomic instincts with confidence scoring, evolves them) and 'when' ("Use when capturing lessons from a session, managing instincts, or promoting them") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ("capturing lessons from a session", "managing instincts", "promoting them into skills, commands, or agents") but a few common variations or synonyms a user might naturally say are missing, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The instinct/hooks/project-scoped niche with specific triggers ("capturing lessons", "promoting instincts") is clearly distinguishable from other skills and unlikely to fire for the wrong skill.	5 / 5
	Total	19 / 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: affaan-m/ECC
Path: skills/continuous-learning-v2/SKILL.md
Commit: e04ea0b

Reviewed: 6 days 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.