recursive-decision-ledger

Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

Quality

57%

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/recursive-decision-ledger/SKILL.md

Quality

Content

75%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 content is well-structured, lean, and actionable with a clear sequenced loop and explicit promotion/validation gates appropriate to a destructive-ops context. Main gap is a few abstract steps ('Run the bounded search') and distributed rather than staged validation.

Suggestions

Define 'effective trial count' and give one concrete shape for 'Run the bounded search' (e.g. sample size / iteration cap) so step 3 is executable rather than abstract.

Make the validate→fix→retry loop explicit in the Rollout Loop (e.g. add a step: 'If replay/freshness gates fail, re-run the bounded search before summarizing') to stage validation as a crisp checkpoint.

Add a one-line pointer format for the ledger artifact path so the append-before-summarize step is concrete (e.g. 'Append to ledgers/rollout-<id>.jsonl').

Dimension	Reasoning	Score
Conciseness	The body is lean with tight section headers, bullet lists, and compact code blocks; the only mild over-explanation is the framing prose ('Preserve the useful part... Remove the unsafe part...'), which is purposeful but could be trimmed.	4 / 5
Actionability	It gives concrete guidance — a field list for the ledger, a 7-step loop, a coherence-mark template, and a summary-shape example — with only minor gaps ('Run the bounded search', 'effective trial count' left abstract).	4 / 5
Workflow Clarity	The Rollout Loop is a clear numbered sequence with explicit validation gates (promotion rules, coherence-mark replay/freshness gates) and a feedback path ('needs replay', downgrade on invalidation); not a 5 only because validation is distributed rather than one crisp validate→fix→retry block.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed; the body is a single self-contained file with well-organized sections and no nested references, just slightly over the 50-line simple-skill threshold that would warrant a 5.	4 / 5
	Total	16 / 20 Passed

Description

40%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 a strong trigger list for a distinct niche but omits any statement of what the skill actually does, capping completeness and specificity. Adding a leading capability clause (e.g., 'Maintains an append-only decision ledger that records...') would lift both.

Suggestions

Lead with a third-person capability statement before the 'Use when' clause so the 'what' is explicit, e.g. 'Maintains an append-only recursive decision ledger recording rollouts, marks, and promotion gates.'

Soften jargon trigger terms or add natural-language synonyms (e.g. 'repeated trials / retries' alongside 'rollouts', 'search over many options' alongside 'high-dimensional search') so users say them naturally.

Add the observable output ('visible evidence trail' / JSONL ledger) as an explicit capability so the 'what' is concrete rather than implied.

Dimension	Reasoning	Score
Specificity	The description names several niche domains ('repeated rollouts', 'high-dimensional search', 'ensemble comparison') but lists no concrete actions — every clause is a trigger context, not a capability, so it 'names the domain but actions are minimal'.	2 / 5
Completeness	It provides a clear 'Use when...' trigger but never states what the skill does — 'only when is present without what', matching the score-2 anchor rather than 3 (which requires a clear what).	2 / 5
Trigger Term Quality	It covers a broad range of scenarios, but many terms ('stochastic optimization', 'local-optima exploration', 'Prime Gauss'-adjacent jargon) are technical jargon rather than phrases a user would naturally say, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	The trigger set is a distinct niche (recursive rollouts with evidence trails) unlikely to fire for unrelated skills, with only minor overlap risk from broad terms like 'recursive reasoning'.	4 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/recursive-decision-ledger/SKILL.md
Commit: d8409a4

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.