planner-closure-backfill

Produce one revision-fenced Planner backfill proposal for either a Detailer replan or task-set closure, with compact Frontdesk status evidence.

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 ./docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_planner/skills/planner-closure-backfill/SKILL.md

Quality

Content

71%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 complete, copy-paste-ready JSON exemplars and clear mode-conditional guidance backed by validation invariants. Its main weaknesses are repeated restatements of the same prohibitions and references to template files that do not exist in the bundle.

Suggestions

Deduplicate the activation-mode prohibitions — state each 'never combine/substitute/exchange modes' rule once in the Rules section and reference it rather than restating across sections.

Either add the referenced 'templates/planner-backfill-detailer-replan.json' and 'templates/planner-backfill.json' files to the bundle or remove the references and rely on the inline exemplars, so references are not broken.

If the host truly owns validation, make that single validation handoff explicit as a final checkpoint step to lift workflow_clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	It does not over-explain known concepts, but the same prohibitions recur repeatedly ('never masquerade', 'never combine the two modes', 'never exchange those activation rules', 'do not treat a closure as a Detailer replacement'), which is more than minor padding; matches the 'mostly efficient but could be tightened' anchor and not a 4 due to the repeated restatements.	3 / 5
Actionability	Two complete JSON exemplars with exact field mappings ('pass -> closure_complete', 'replan_required -> task_set_replanned') and a full copy-paste-ready structure cover both activation modes, matching the 'fully executable, copy-paste ready, covers common cases' anchor.	5 / 5
Workflow Clarity	A clear mode-conditional sequence (select mode -> use only authority fields -> preserve accepted facts -> emit one fenced section) with rule-based invariants acting as validation ('pass requires empty unresolved/blocker/replan fields', return 'revision_conflict'), matching the 'clear sequence with most checkpoints present' anchor; not a 5 because checks are rule invariants rather than explicit validate->fix->retry steps.	4 / 5
Progressive Disclosure	Sections are organized, but the body references 'templates/planner-backfill-detailer-replan.json' and 'templates/planner-backfill.json' that are not present in the bundle, while also inlining two full exemplars — broken references plus duplicated inline content matches the 'some structure, references present but not clearly signaled, content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

63%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, complete, and highly distinct within its agent ecosystem, but its trigger terms are internal jargon rather than natural user phrases. It clearly states what it does and the two activation conditions that trigger it.

Suggestions

Add a plain-language 'Use when...' clause naming the controller activation modes in user-recognizable terms so the trigger reads as a natural condition rather than only internal component names.

Soften or pair the jargon ('Planner backfill', 'Detailer replan', 'Frontdesk') with one synonym a non-specialist would recognize to improve trigger_term_quality.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions/modes — 'Produce one revision-fenced Planner backfill proposal', 'Detailer replan', 'task-set closure', 'compact Frontdesk status evidence' — matching the 'lists several specific actions, minor gaps' anchor; not a 5 because coverage is narrow and entirely internal.	4 / 5
Completeness	Answers both 'what' (produce a proposal with Frontdesk status evidence) and 'when' ('for either a Detailer replan or task-set closure', an explicit mode-based trigger), matching the 'has both what and when, when could be more explicit' anchor; not a 5 because the 'when' is mode-conditional rather than a natural user-situation trigger.	4 / 5
Trigger Term Quality	Terms are pure internal jargon ('Planner backfill', 'Detailer replan', 'Frontdesk status') that no end user would naturally say, analogous to the 'document object model manipulation' anchor; not a 1 only because the two named activation modes are more specific than generic keywords.	2 / 5
Distinctiveness Conflict Risk	A clear niche with two exact activation modes ('detailer_replan', 'task_set_closure') and a fenced one-proposal output contract, giving minimal conflict risk with other skills; matches the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	15 / 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: SeemSeam/claude_codex_bridge
Path: docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_planner/skills/planner-closure-backfill/SKILL.md
Commit: 01d5b1c

Reviewed: about 20 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.