plan-create

Create `.context/plans/*.md` files with standard YAML frontmatter, phases/tasks/waves decomposition, and post-creation validation. Infers section conventions from existing plans in `.context/plans/` to match the local style. Integrates with plan-review for a create → review → iterate loop. Triggers: 'create a plan', 'new plan', 'draft a plan', 'plan scaffold', 'write a plan'. Do NOT use for plans outside `.context/plans/`, ephemeral notes, or the main project SKILL.md.

Quality

86%

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

Quality

Content

73%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.

A well-structured instructional skill: the workflow is clearly sequenced with strong validation checkpoints, and detailed material (grading rubric, section conventions, scaffold template) is correctly split into real one-level-deep bundle files. The main costs are repetition of the effort/value/themes guidance across four sections and a mismatch between the referenced validation script and the script actually shipped in the bundle.

Suggestions

Consolidate the effort/value/themes guidance into a single pointer to references/grading-effort-value-themes.md (keep one full statement, e.g. in step 1, and reference it tersely in Verification, Mindset, and Anti-Patterns) to cut roughly a page of repetition.

Reference the bundle's own scripts/validate-plan-scaffold.sh (or explain when it applies vs. the external context-index validate-context-frontmatter.sh) so validation is executable without the external skill present.

Trim the SYMPTOM/CONSEQUENCE/WHY blocks in Anti-Patterns to the WHY line plus BAD/GOOD pairs, and either link or drop the bare mentions of planning-flow.md and migrate-off-tessl-eval-2026-06-29.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and specific field values, but the effort/value/themes guidance is repeated in step 1, verification items 6-7, Mindset, and an Anti-Pattern, and the Anti-Patterns section pads each entry with SYMPTOM/CONSEQUENCE/WHY explanations that partially restate each other.	3 / 5
Actionability	Concrete, executable guidance dominates (the grep frequency command, exact frontmatter fields with allowed values, template and schema paths, a confirmation output block), but the validation step depends on an external skill's script ('validate-context-frontmatter.sh' from context-index) while the bundle's own scripts/validate-plan-scaffold.sh is never referenced.	4 / 5
Workflow Clarity	Six numbered steps are clearly sequenced with an explicit validation checkpoint and error-recovery loop ('If validation fails, fix the frontmatter and re-run. Do not proceed until validation passes'), reinforced by a dedicated 7-point Verification checklist.	5 / 5
Progressive Disclosure	Good structure with a well-signaled References table ('When to Use' column) pointing to real, one-level-deep bundle files (both references files, the template, and the schema all exist), but scripts/validate-plan-scaffold.sh is orphaned from SKILL.md and the body carries unlinked mentions of 'planning-flow.md' and 'migrate-off-tessl-eval-2026-06-29.md'.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: concrete third-person capability statements, natural trigger phrases with synonym coverage, and an explicit negative-scope clause that cleanly separates it from adjacent skills. Nothing essential is left implicit.

Dimension	Reasoning	Score
Specificity	It lists multiple specific concrete actions — 'Create .context/plans/*.md files with standard YAML frontmatter, phases/tasks/waves decomposition, and post-creation validation' plus 'Infers section conventions from existing plans' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Both questions are explicitly answered: what it does (create plan files with frontmatter, decomposition, validation, convention inference, plan-review integration) and when to use it (explicit 'Triggers:' with concrete phrases, plus negative triggers 'Do NOT use for plans outside .context/plans/').	5 / 5
Trigger Term Quality	The Triggers clause covers the natural phrasing users would actually say with synonym variation: 'create a plan', 'new plan', 'draft a plan', 'plan scaffold', 'write a plan'.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (plans in .context/plans/ specifically) and the explicit exclusion clause ('Do NOT use for plans outside .context/plans/, ephemeral notes, or the main project SKILL.md') minimizes overlap with adjacent skills like plan-review or the skill template.	5 / 5
	Total	20 / 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
relative_links	Relative link issues: 2 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 4 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: pantheon-org/tekhne
Path: skills/project-mgmt/plan-create/SKILL.md
Commit: a1083f4

Reviewed: 4 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.