CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

iterative-planner

State-machine driven iterative planning and execution for complex coding tasks. Cycle: Explore → Plan → Execute → Reflect → Pivot. Filesystem as persistent memory. Use for multi-file tasks, migrations, refactoring, failed tasks, or anything non-trivial.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

The protocol content is exceptionally actionable and the workflow is the best-case anchor: explicit state machine, mechanical gates, and layered recovery procedures. The clear weakness is conciseness — the body spends large token budgets on self-justifying meta-commentary (known-gap disclosures, historical rationale for field formats, repeated legacy-name callouts) that directly contradicts its own "context window = RAM" principle, and the spine carries tables that should live in references.

Suggestions

Move the self-justifying meta-disclosures (the unscoped-Bash known-gap note, the changelog step-field no-prefix rationale, the leash-override exception history) out of SKILL.md into a reference or project changelog — they explain design history, not runtime behavior, and cost resident tokens on every activation.

Relocate the File Lifecycle Matrix and File Ownership table bodies to references/file-formats.md (both are lookup material, not activation-time reading), keeping only the read-before-write rule and a pointer in the spine.

Collapse the repeated legacy `plan_` directory-name callouts (appearing in the plan-dir definition, bootstrap, recovery step 0, and Git Integration) into a single note in references/file-formats.md and reference it once.

DimensionReasoningScore

Conciseness

The ~490-line body is noticeably verbose: it carries several padded meta-disclosures — the "Known gap — unscoped Bash on read-only agents" paragraph, the multi-paragraph justification for why the changelog `step` field carries no plan-id prefix ("Do not 'fix' the apparent inconsistency..."), the "Disclosed exception — the leash-override 'continue'" digression, and repeated legacy `plan_` naming callouts across at least four sections. None of this is explanation of concepts Claude already knows (so not a 1), but the skill ironically preaches "Context Window = RAM. Write to disk immediately" while inlining substantial rationale that belongs on disk.

2 / 5

Actionability

Fully executable throughout: copy-paste-ready commands (`node <skill-path>/scripts/bootstrap.mjs new "goal"`, `--pre-step`, `reset-attempts`), exact gate semantics ("Exit code 2 emits one of four `GATE:FAIL` slugs — `[no-plan]`, `[wrong-state]`, `[leash-cap]`, `[iteration-cap]`"), a complete file tree, per-file lifecycle and ownership matrices, and a worked commit-tag derivation ("`plan-2026-07-14T051317-317362c4` → `[plan-2026-07-14-317362c4/iter-3/step-2] desc`"). `<skill-path>` resolution is itself specified. Anchor 5: specific examples cover the common cases.

5 / 5

Workflow Clarity

Exemplary sequencing and validation: a Mermaid state machine plus a transition table with explicit triggers, a Pre-Step Gate that hard-blocks on failure, a "4-item Post-Step Gate", the REFLECT "3-phase gate: Gate-In (7 mandatory reads), Evaluate... then Gate-Out", and feedback loops for error recovery (revert-first leash with 2 attempts, 3-Strike Rule, a 13-item numbered recovery-from-context-loss procedure). Matches anchor 5 (explicit validation steps, feedback loops, checklists); not 4 because checkpoints are explicit at every transition, not merely most.

5 / 5

Progressive Disclosure

Good bundle structure scored against the actual files: 9 real `references/*.md` files all exist and are annotated in the References section, per-state detail is correctly pushed to `scripts/modules/state-<state>.md` via the emit-state router (all 5 modules verified present), and `agents/ip-*.md` is explicitly framed as an optional install with a documented fallback rather than a broken path. Not 5 because the SKILL.md body itself still inlines substantial detail — the File Lifecycle Matrix, File Ownership table, and compression-protocol format blocks — that belongs one level deeper, leaving the "spine" dense rather than overview-shaped.

4 / 5

Total

16

/

20

Passed

Description

83%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.

A strong description: concrete mechanism vocabulary, an explicit "Use for..." trigger clause, and a distinctive state-machine framing. Its main weaknesses are the broad "anything non-trivial" catch-all (which slightly dilutes both trigger quality and distinctiveness) and the absence of any concrete operational detail about what the skill actually does to files or commands.

DimensionReasoningScore

Specificity

Names the domain and several concrete mechanism components — "State-machine driven iterative planning and execution", the five named cycle states "Explore → Plan → Execute → Reflect → Pivot", and "Filesystem as persistent memory" — but never enumerates the actual operations (which files are written, what commands run). Anchor 4 (several specific actions, minor coverage gaps) fits; 5 requires comprehensive concrete actions, 3 covers only 1-2.

4 / 5

Completeness

Explicitly answers both: "what" — state-machine driven iterative planning/execution with a named cycle and filesystem-as-memory design; "when" — a literal "Use for..." clause with concrete trigger phrases (multi-file tasks, migrations, refactoring, failed tasks). Matches the anchor-5 example structure exactly; not 4 because the "when" is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

"Use for multi-file tasks, migrations, refactoring, failed tasks, or anything non-trivial" gives good natural-term coverage (users do say "refactoring", "migrations", "multi-file"), but common variations like "large change", "codebase-wide", or "stuck task" are missing and "anything non-trivial" is a catch-all rather than a trigger term. Above anchor 3 (which expects missing synonyms), below anchor 5 (comprehensive synonyms/extensions).

4 / 5

Distinctiveness Conflict Risk

The iterative-planning state-machine niche with its named cycle is mostly distinct from typical single-task skills, but "anything non-trivial" and "complex coding tasks" are broad enough to overlap with general planning or orchestration skills. Minor overlap risk with closely related skills = anchor 4; anchor 5 would require a clear niche with distinct triggers and no broad catch-alls.

4 / 5

Total

17

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 7 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

NikolasMarkou/iterative-planner

Path

src/SKILL.md

Reviewed

Table of Contents

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.