planning-with-files

planning-with-files is a Task tracking & backlogs skill for AI agents, published by OthmanAdi in the planning-with-files repository on GitHub. Skillspace rates planning-with-files B (82/100) and it passed the safety scan; a judge model has also reviewed it.

Manus-style file-based planning for complex tasks. Creates and maintains task_plan.md, findings.md, and progress.md under .kiro/plan/. Use when planning, breaking down work, resuming a multi-step task, tracking phases, or restoring context after compaction. Trigger phrases include start planning, continue task, resume work, current phase, restore context.

Grade
B
Quality
82 / 100
Safety
Passed
GitHub stars
25,589

Placed #4 of 6 in the judged category final for Task tracking & backlogs.

Not launch-quality. It is graded B with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
91 / 100
Maturity
Packaged: licensed, with a version or references
Security scan
No issues found
License
MIT
Adoption
Adopted by 3 other repositories, in 2 collections
Scope
Vendor-specific: built around one product. Documents file-based planning using Kiro IDE's own Agent Skills.

Judge review

Placed #4 of 6 in the judged category final for Task tracking & backlogs.

  • Trigger9090
  • Instructions9090
  • Specificity8787
  • Safety8585
  • Disclosure7878
  • Maintenance7878
Cleanest of the planning-with-files ports, with explicit trigger phrases, numbered steps, and an honest idempotency note on its bootstrap script.
Cleanest of the planning-with-files ports, with explicit trigger phrases, numbered steps, and an honest idempotency note on its bootstrap script.

Not checked yet

  • No blind task eval yet
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.