technical-writer
Write or review technical documents, including READMEs, system overviews, and skill files.
Skill by cederberg
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cederberg-technical-writer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/technical-writer
Tools it pre-approves 5
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Agent,Read,Write,Bash,Glob
What's inside
- Skill name
technical-writer- Description
- Write or review technical documents, including READMEs, system overviews, and skill files.
- License
- MIT
- Allowed tools
- Agent,, Read,, Write,, Bash,, Glob
- Instructions
- 226 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (20)
- SKILL.md
- checklist.md · references/modes/other/
- instructions.md · references/modes/other/
- checklist.md · references/modes/overview/
- examples.md · references/modes/overview/
- instructions.md · references/modes/overview/
- template.md · references/modes/overview/
- checklist.md · references/modes/readme/
- examples.md · references/modes/readme/
- instructions.md · references/modes/readme/
- template.md · references/modes/readme/
- checklist.md · references/modes/skill-writer/
- examples.md · references/modes/skill-writer/
- instructions.md · references/modes/skill-writer/
- template.md · references/modes/skill-writer/
- researcher.md · references/roles/
- reviewer.md · references/roles/
- writer.md · references/roles/
- abstraction-rules.md · references/rules/
- style-guide.md · references/rules/
SKILL.md (first lines)
## Mode Selection
| Mode | When to use |
| ---------------- | ----------------------------------------------------------- |
| **readme** | Write or rewrite a project-level README |
| **overview** | Write a technical overview of a system, subsystem, or topic |
| **skill-writer** | Write a new skill file or review and polish an existing one |
| **other** | Write any other technical document |
If the user specifies a mode, use it. Otherwise, infer from the request:
- "write a README" / "document this project" / "generate a README" → `readme`
- "write a technical overview" / "document this system" → `overview`
- "write a skill" / "create a skill" / "new skill" → `skill-writer`
If no other mode matches, use `other` as the default.
## Variable Setup
Set these path variables once and use throughout:
```
MODE={{detected-mode}}
MODE_DIR=references/modes/$MODE
WORK_DIR={{session working directory}}
```
Pass `$WORK_DIR` and `$MODE_DIR` to all sub-agents.
Read this skill first, then read `$MODE_DIR/instructions.md` and apply any
mode-specific overrides before running the workflow.
### Review Variant
When the user provides an existing document to review, ask which variant to run
unless context makes the intended variant clear. Use these as default variants:
- **Validity** — run Discovery and Research, then review the existing document
directly without a writer pass
- **Revision** — edit or rewrite an existing document from user feedback, then
run review
- **Clarity** — run reviewer directly on existing document without codebase
research
Mode instructions may override variant names and phase entry behavior.
| Phase | Write | Validity | Revision | Clarity |
| ------------ | ----- | -------- | -------- | ------- |
| 1: Discovery | Run | Run | Skip | Skip |
| 2: Research | Run | Run | Skip | Skip |
| 3: Write | Run | Skip | Run | Skip |
| 4: Review | Run | Run | Run | Run |
---
## Your Role
Act as the workflow manager. Launch sub-agents and confirm that each phase has
produced non-empty output. Route, delegate, and verify. Do not read or
synthesize file contents.
Read only these four files:
1. `$MODE_DIR/instructions.md` — workflow configuration
2. A user-provided existing document — when the user supplies one for review or
as a baseline
3. `$WORK_DIR/discovery.md` — researcher scope definition
4. `$WORK_DIR/review.md` — revision decision
Pass all other files — role files, rule files, templates, examples, checklists,
research outputs, and drafts — as file paths to sub-agents. Do not open those
files.
## Workflow: Four Phases, Multiple Sub-Agents
Use a separate, isolated **general-purpose** sub-agent for each phase. Do not
use Explore agents — all phases write output files to `$WORK_DIR` and require
Write access.
If `$MODE_DIR/instructions.md` defines phase behavior (for example, Pre-flight
steps or mode-specific discovery/research flow), follow it.
---
### Phase 1: Discovery
Run a **discovery sub-agent** to enumerate the project's components,
integrations, and existing documentation.
Launch the sub-agent with:
- `$WORK_DIR` — the output directory path
- Instructions to scan the codebase for application modules, external system
references, and existing documentation files
The discovery sub-agent writes its output to `$WORK_DIR/discovery.md` with four
sections:
- **Modules & Services** — all application modules, services, or major
components. One line each, no descriptions.
- **External Systems** — all external systems referenced in config, code, or
documentation. One line each, no descriptions.
- **Processes & Workflows** — named processes, jobs, pipelines, or multi-step
operations the system performs. One line each: process name and trigger (e.g.,
"Order Provisioning — triggered by incoming order event", "Nightly
Reconciliation — scheduled daily"). Include both primary and background
processes.
- **Documentation & Specs** — any existing documentation files worth consulting:
READMEs, OpenAPI/WSDL specs, architecture docs, wikis, significant
configuration files. One line each with relative path.
Read `$WORK_DIR/discovery.md` and use it to define researcher scopes in Phase 2.
---
### Phase 2: Research
Read the Research Topics section of `$MODE_DIR/instructions.md` to determine
researcher assignments. Each assignment includes a topic name, description, andFrom cederberg/incubator, MIT.
More from cederberg/incubator
- 0.570score
refactor
cederberg
Multi-pass convergent refactoring of a specific piece of code.
SkillAFreshness: AClaude Code +9 - 0.565score
review-instructions
cederberg
Review a prompt, skill, or other instructions for problems.
SkillAFreshness: AClaude Code +9 - 0.564score
review-session
cederberg
Analyze agent session logs for knowledge, guideline, and capability gaps.
SkillAFreshness: AClaude Code +9 - 0.558score
bump-deps
cederberg
Update each outdated dependency in a separate, minimal commit.
SkillAFreshness: AClaude Code +9 - 0.524score
investigate
cederberg
Guide a structured, iterative technical investigation using hypothesis tree reasoning.
SkillBFreshness: BClaude Code +9 - 0.518score
review-doc
cederberg
Review a document for internal consistency, brevity, clarity, and usefulness.
SkillBFreshness: BClaude Code +9 - 0.471score
discuss
cederberg
Facilitate a focused, structured discussion on a topic.
SkillCFreshness: CClaude Code +9 - 0.470score
agent-init
cederberg
Analyze a project and produce AGENTS.md and Makefile.
SkillCFreshness: CClaude Code +9 - 0.469score
interview-me
cederberg
Conduct a deep, structured interview to reach shared understanding of a plan or topic, then document the outcome.
SkillCFreshness: CClaude Code +9 - 0.467score
brainstorm
cederberg
Open-ended idea generation without filtering for validity.
SkillCFreshness: CClaude Code +9 - 0.464score
what-we-forgot
cederberg
Scans the current conversation from the beginning for missed instructions, unresolved work items, and forgotten ideas.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cederberg/incubator
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cederberg
- 0.570score
refactor
cederberg
Multi-pass convergent refactoring of a specific piece of code.
SkillAFreshness: AClaude Code +9 - 0.565score
review-instructions
cederberg
Review a prompt, skill, or other instructions for problems.
SkillAFreshness: AClaude Code +9 - 0.564score
review-session
cederberg
Analyze agent session logs for knowledge, guideline, and capability gaps.
SkillAFreshness: AClaude Code +9 - 0.558score
bump-deps
cederberg
Update each outdated dependency in a separate, minimal commit.
SkillAFreshness: AClaude Code +9 - 0.524score
investigate
cederberg
Guide a structured, iterative technical investigation using hypothesis tree reasoning.
SkillBFreshness: BClaude Code +9 - 0.518score
review-doc
cederberg
Review a document for internal consistency, brevity, clarity, and usefulness.
SkillBFreshness: BClaude Code +9
Cite this page
technical-writer skill. Agent Mart. https://agentmart.dev/skills/cederberg-technical-writer (last updated 2026-10-24)