Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Planning Research

ASecurity

Research a repository and, only when requested, produce an evidence-backed staged implementation plan.

11 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgosecurity

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add startmeupai/swe-agents --skill planning-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Planning Research?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Planning Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/startmeupai-planning-research/badge)](https://www.skillsdirectory.com/skills/startmeupai-planning-research)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: planning-research
description: Research a repository and, only when requested, produce an evidence-backed staged implementation plan.
---

# Planning Research

## Trigger Conditions

Use for codebase research, scope discovery, effort analysis, or plan creation.
Choose read-only research mode when the caller asks a bounded factual question;
choose planning mode only when the caller explicitly requests a plan.

## Required Inputs

- Problem statement, target scope, constraints, and acceptance criteria.

## Workflow

1. Select read-only research mode or planning mode from the requested outcome.
2. Restate the question, then separate in-scope, out-of-scope, assumptions, and
   missing inputs.
3. Search implementation, tests, configuration, docs, and prior plans and reports.
4. Identify reusable contracts and read the implementation of every shared
   helper the answer or plan depends on; confirm it handles the data shapes in
   scope.
5. Confirm runtime prerequisites such as seeded records, configuration, and
   feature flags; record each missing one as a finding or a plan task.
6. Record evidence and risks, including security and deployment effects.
7. In research mode, rank findings on the
   finding severity scale from the core rules and report a summary, ranked findings, and limitations.
8. In planning mode only, write stages in the format below with atomic tasks,
   dependencies, and separate verification gates.

## Stage Format

```markdown
## Stage 2: Focused Tests

**Goal:** Prove allowed and denied settings updates at the mutation boundary.
**Assigned Specialist:** `test-agent`
**Dependencies:** Stage 1
**Status:** Pending

- [ ] Add positive and negative integration tests.
- [ ] Run the focused test command and record its result.
```

- Give each stage one dominant outcome and the narrowest owning persona. Split
  a stage that mixes unrelated workstreams.
- When a coupled stage needs a second specialist, keep one assigned owner and
  suffix that task with `(Specialist: <persona>)`.
- Write every task and gate as `- [ ]`; no other status markers.

## Deterministic Checks

- Confirm every referenced file exists. In planning mode, run the project's
  plan checker when it has one (for example `pnpm check:plans`) to validate
  checkbox syntax, stage fields, and assigned personas.

## Safety and Permission Boundaries

- Research is read-only; planning does not authorize implementation or external
  writes. A `research-agent` invocation must not create a plan.

## Required Evidence

- File references for current behavior and explicit labels for unverified assumptions.

## Completion Condition

- Read-only research is complete when the bounded question has an
  evidence-backed answer and limitations. Planning is complete when the plan is
  bounded, evidence-backed, owned, sequenced, and ready for critique.

## Example

`Plan Project Alpha team settings after researching existing RBAC and UI patterns.`
See `examples/plans/staged-implementation-plan.md` in the reference repository.

Attribution

startmeupaistartmeupai
View sourceSee grades on GitHubMore from startmeupai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →