realign

Project guide direction line via three-horizon fusion. Invoke with /realign.

Quality

62%

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 ./epistemic-cooperative/skills/realign/SKILL.md

Quality

Content

60%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 precisely sequenced, actionable protocol with strong approval-gating and feedback loops for a destructive write, but it is noticeably verbose because the phase flow is re-expressed in multiple redundant formal notations. Progressive disclosure is solid given the self-contained single-file design, though the formal blocks add length without proportionate navigation benefit.

Suggestions

Collapse the FLOW, MORPHISM, PHASE TRANSITIONS, and TOOL GROUNDING blocks into a single phase-transition reference; the prose Protocol already conveys the sequence, so the duplicated formal restatements are pure padding.

Move the TYPES / MODE STATE / COMPOSITION formal definitions into a separate reference file (e.g. references/types.md) and link to it from the Protocol, reducing the inline token load while preserving precision.

Tighten abstract phrasing like 'scan the configured channels and aggregate the direction-bearing signals' into a concrete channel-by-channel recipe (e.g. 'grep open issues for direction-bearing terms; read recent PR review summaries').

Dimension	Reasoning	Score
Conciseness	The body restates the same phase flow three times in different formal notations (FLOW, MORPHISM, PHASE TRANSITIONS, TOOL GROUNDING) that duplicate the Phase 0-3 prose, and leans heavily on bespoke vocabulary (Periagoge, Constitution interaction, horizons); this matches anchor 2 ('noticeably verbose; several unnecessary explanations or padded sections') rather than 3 because the redundant formal blocks are clearly trimmable.	2 / 5
Actionability	Concrete, copy-ready interaction templates (the option menus in Phase 2 and Phase 3) and exact per-phase outputs give mostly executable guidance; it falls short of anchor 5 only because some steps remain abstract ('scan the configured channels and aggregate the direction-bearing signals').	4 / 5
Workflow Clarity	The Phase 0→1→2→3 sequence is explicit with an approval gate before the destructive write (Rule 5), bounded shaping (5) and modify (3) loops, a rollback hint, and convergence evidence; it fits anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') rather than 5 because the validation is consensual approval rather than a verify→fix→retry loop.	4 / 5
Progressive Disclosure	No bundle files exist, so all content is inline, but the file is well-sectioned (Definition, When to Use, Distinction, Protocol, Storage Reference, Rules, UX Safeguards) with clear headers and one-level structure; this fits anchor 4 ('good structure; most content appropriately placed; minor organization gaps') rather than 5 because the long inline formal-notation blocks could plausibly live in a reference file.	4 / 5
	Total	14 / 20 Passed

Description

48%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 terse and identifies a clear niche with an explicit invocation trigger, but it relies on abstract jargon ('three-horizon fusion') and lacks an explicit 'Use when...' clause, capping completeness and specificity. It is distinct but under-specified compared to the strongest examples.

Suggestions

Reword 'three-horizon fusion' into plain concrete actions, e.g. 'Scans the inscribed direction, external work signals, and your present understanding, fuses them into a candidate with a per-horizon trace, and writes the confirmed line back to the project guide.'

Add an explicit 'Use when...' clause stating when to invoke, e.g. 'Use when the project guide's direction line no longer reflects current work, recent reviews, or your present sense of the project.'

Include natural trigger synonyms (e.g. 'project direction drifted', 'direction line is stale') so the skill surfaces for the phrases users actually say.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Project guide direction line') and one operation ('three-horizon fusion'), but 'three-horizon fusion' is abstract jargon rather than a list of concrete actions; it sits between anchor 2 ('names the domain but actions are minimal or generic') and anchor 3, leaning toward 2 because no plain concrete actions (scan, elicit, shape, write) are enumerated.	2 / 5
Completeness	The 'what' is weakly present ('Project guide direction line via three-horizon fusion') and the 'when' is only implied by 'Invoke with /realign' rather than an explicit 'Use when...' clause; per the rubric a missing 'Use when...' clause caps completeness at 3, and it does not clearly fit anchor 4.	3 / 5
Trigger Term Quality	It provides an explicit invocation trigger ('Invoke with /realign') plus the natural phrase 'project guide direction line', but it omits common variations/synonyms a user might say ('project direction is stale', 'direction drifted'), matching anchor 3 ('some relevant keywords but missing common variations or synonyms').	3 / 5
Distinctiveness Conflict Risk	The narrow niche ('project guide direction line') and distinct '/realign' trigger make it mostly distinguishable from adjacent skills, with only minor overlap risk against /probe and /induce, fitting anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5 because the terse description does not fully articulate the distinct triggers.	4 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: jongwony/epistemic-protocols
Path: epistemic-cooperative/skills/realign/SKILL.md
Commit: 10abcb3

Reviewed: 5 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.