Not in the top 1,000 by GitHub stars

yanuarihsanxz-tech/prd-toolkit

Portable PRD foreman for AI agents: testable specifications, specialist routing, revision comparison, and verifiable builder handoffs.

Claude Code Codex Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 7a57d4405bef

No earlier version was observed for comparison.

Compare on GitHub

`prompts/SKILL.md`

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 7a57d4405bef

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 7a57d4405bef10246f8ac9e0f30ac7267ec90f74

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/yanuarihsanxz-tech/prd-toolkit.git .hotskills/yanuarihsanxz-tech-prd-toolkit && git -C .hotskills/yanuarihsanxz-tech-prd-toolkit checkout --detach 7a57d4405bef10246f8ac9e0f30ac7267ec90f74
# Copy each selected skill directory from .hotskills/yanuarihsanxz-tech-prd-toolkit into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/yanuarihsanxz-tech/prd-toolkit.git .hotskills/yanuarihsanxz-tech-prd-toolkit && git -C .hotskills/yanuarihsanxz-tech-prd-toolkit checkout --detach 7a57d4405bef10246f8ac9e0f30ac7267ec90f74
# Copy each selected skill directory from .hotskills/yanuarihsanxz-tech-prd-toolkit into .agents/skills/<skill-name>/

11GitHub stars

Not availablestars in 7 days

2skills in this repository

1commit in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

prd-maker /
prd-generator prompts

How it works

Choose a skill

prd-maker

When your agent uses it

Prepare a self-contained PRD from conversation or existing-project context. Use for requests to write, revise, or review a PRD or specification, including reworks and bug fixes. Honors analysis-only requests. Validation, owner summary, and product flowchart are automatic. Specification only; it does not build.

What it loads into context

Frontmatter

69 tokens

Always available to the agent

SKILL.md

1,293 tokens

When the skill is activated

Reference documents

70,911 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

One-Call Default
Generate
Context And Efficiency

Scripts executed separately

evals/real-cases/csv-total/before.mjs
evals/real-cases/csv-total/candidate.mjs
evals/real-cases/line-summary/candidate.mjs
package.json
scripts/authority-policy.mjs
scripts/compare-prd.mjs
scripts/evaluate.mjs
scripts/export-toolkit.mjs
scripts/local-task-runner.mjs
scripts/prd.mjs
scripts/preview-prd.mjs
scripts/run-tests.mjs
scripts/validate-prd.mjs
scripts/validate-toolkit.mjs
tests/authority-policy.test.mjs
tests/change-integration.test.mjs
tests/compare-prd.test.mjs
tests/distribution.test.mjs
tests/evaluate.test.mjs
tests/local-task-runner.test.mjs
tests/prd.test.mjs
tests/preview-prd.test.mjs
tests/real-cases.test.mjs
tests/validate-prd.test.mjs
tests/validate-toolkit.test.mjs

Files

.gitattributesasset19 bytes
.github/ISSUE_TEMPLATE/bug_report.mddoc613 bytes
.github/ISSUE_TEMPLATE/enhancement.mddoc552 bytes
.github/pull_request_template.mddoc529 bytes
.github/workflows/check.ymlasset536 bytes
.gitignoreasset147 bytes
.reasonix/commands/prd/audit.mddoc1,124 bytes
.reasonix/commands/prd/discover.mddoc1,191 bytes
.reasonix/commands/prd/execute.mddoc1,475 bytes
.reasonix/commands/prd/generate.mddoc1,216 bytes
.reasonix/commands/prd/improve.mddoc1,116 bytes
.reasonix/commands/prd/tasks.mddoc1,166 bytes
.reasonix/commands/prd/validate.mddoc1,095 bytes
AGENTS.mddoc6,649 bytes
BASELINE.mddoc10,221 bytes
CHANGELOG.mddoc22,892 bytes
CLAUDE.mddoc270 bytes
DECISIONS.mddoc6,942 bytes
LICENSEasset1,081 bytes
PROGRESS.mddoc10,320 bytes
PROJECT_CONTEXT.mddoc8,793 bytes
README.mddoc11,822 bytes
SKILL.mdcore6,370 bytes
SKILL.mdcore6,370 bytes
docs/AUTHORITY_POLICY.mddoc2,085 bytes
docs/CHANGE_CONTRACT.mddoc11,419 bytes
docs/CONTRIBUTING.mddoc12,208 bytes
docs/CONVERSATION_TO_UNIVERSAL_PRD_LESSONS.mddoc2,526 bytes
docs/DISTRIBUTION.mddoc5,873 bytes
docs/GETTING_STARTED.mddoc6,699 bytes
docs/INDEX.mddoc8,606 bytes
docs/PORTABLE_WORKFLOW.mddoc7,052 bytes
docs/REASONIX_ADAPTER.mddoc6,610 bytes
docs/archive/README.mddoc2,231 bytes
evals/efficiency-rework-2026-09-12.mddoc3,591 bytes
evals/forward-test-report.mddoc4,838 bytes
evals/generator-regression-cases.jsonasset7,359 bytes
evals/git-readiness-2026-09-27.mddoc3,856 bytes
evals/real-cases/README.mddoc6,595 bytes
evals/real-cases/csv-total/BRIEF.mddoc1,753 bytes
evals/real-cases/csv-total/PRD.mddoc13,135 bytes
evals/real-cases/csv-total/before.mjsruns549 bytes
evals/real-cases/csv-total/candidate.mjsruns2,178 bytes
evals/real-cases/csv-total/case.jsonasset2,808 bytes
evals/real-cases/line-summary/BRIEF.mddoc1,335 bytes
evals/real-cases/line-summary/PRD.mddoc11,023 bytes
evals/real-cases/line-summary/candidate.mjsruns839 bytes
evals/real-cases/line-summary/case.jsonasset2,455 bytes
evals/release-3.2.0.mddoc7,735 bytes
evals/research-2026-11-03.mddoc4,005 bytes
examples/app-prd-example.mddoc35,995 bytes
examples/prd-handoff-example.mddoc2,237 bytes
examples/tool-prd-example.mddoc28,157 bytes
layout/AUDIT_IMPLEMENTATION.mddoc4,458 bytes
layout/DISCOVER_PRODUCT.mddoc2,664 bytes
layout/EXECUTE_TASKS.mddoc5,202 bytes
layout/GENERATE_PRD.mddoc1,093 bytes
layout/GENERATE_TASKS.mddoc4,944 bytes
layout/IMPROVE_PRD.mddoc3,365 bytes
layout/INDEX.mddoc1,130 bytes
layout/VALIDATE_PRD.mddoc2,081 bytes
package.jsonruns669 bytes
schemas/generator-regression.schema.jsonasset2,810 bytes
schemas/prd-frontmatter.schema.jsonasset1,591 bytes
schemas/task-plan.schema.jsonasset7,471 bytes
schemas/task-state.schema.jsonasset12,533 bytes
scripts/authority-policy.mjsruns4,233 bytes
scripts/compare-prd.mjsruns23,681 bytes
scripts/evaluate.mjsruns11,524 bytes
scripts/export-toolkit.mjsruns4,416 bytes
scripts/local-task-runner.mjsruns47,670 bytes
scripts/prd.mjsruns7,590 bytes
scripts/preview-prd.mjsruns3,905 bytes
scripts/run-tests.mjsruns1,235 bytes
scripts/validate-prd.mjsruns37,134 bytes
scripts/validate-toolkit.mjsruns45,746 bytes
templates/full.mddoc15,243 bytes
templates/lite.mddoc10,563 bytes
templates/project-decisions.mddoc1,158 bytes
templates/project-progress.mddoc1,870 bytes
templates/task-plan.jsonasset6,357 bytes
tests/authority-policy.test.mjsruns5,004 bytes
tests/change-integration.test.mjsruns4,080 bytes
tests/compare-prd.test.mjsruns31,395 bytes
tests/distribution.test.mjsruns7,098 bytes
tests/evaluate.test.mjsruns7,014 bytes
tests/local-task-runner.test.mjsruns20,452 bytes
tests/prd.test.mjsruns4,022 bytes
tests/preview-prd.test.mjsruns3,382 bytes
tests/real-cases.test.mjsruns3,924 bytes
tests/validate-prd.test.mjsruns17,299 bytes
tests/validate-toolkit.test.mjsruns7,491 bytes

Read SKILL.md


# PRD Maker

This is the entry point when the user references this folder. Resolve toolkit
paths relative to this file. Work in the user's target project, not this toolkit.
The current request determines the operation; attaching a file alone does not
authorize implementation, installation, deployment, or external writes.

## One-Call Default

When the user calls this toolkit after discussing a product, read the existing
conversation and relevant target files. Do not ask them to repeat scope, choose
Full/Lite, request validation, request a summary/flowchart, or say "do not build".
Those behaviors are built in. A toolkit invocation with resolved context means
prepare the PRD; an incidental link or quoted mention alone is not an invocation.

View the complete source on GitHub

prd-generator

When your agent uses it

Compatibility entry for the PRD Maker. Generate, improve, review, or build from a PRD using the operation requested by the user.

What it loads into context

Frontmatter

36 tokens

Always available to the agent

SKILL.md

132 tokens

When the skill is activated

Reference documents

18,525 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Files

../SKILL.mddoc6,370 bytes
PHASE_GATED_TASK_RUNNER.mddoc12,168 bytes
PRD_GENERATOR_PROMPT.mddoc16,283 bytes
PRD_VALIDATION_CHECKLIST.mddoc17,060 bytes
RELIABILITY_GUIDE.mddoc22,342 bytes
RESEARCH_AND_TOOL_ROUTING.mddoc16,355 bytes
SKILL.mdcore647 bytes

Read SKILL.md


# PRD Maker Compatibility Entry

Read [the canonical PRD Maker skill](../SKILL.md) and follow exactly the operation
the user requested. This path remains for existing agent adapters and references;
it does not define a second workflow.

Research-only requests remain read-only. PRD generation does not implement code.
New local builds use the host's native plan by default. Existing toolkit runner
plans/states retain their recorded approval, failure, and recovery contracts.

View the complete source on GitHub

Skills included

prd-maker
prd-generator

Repository facts

License: MIT
Created: Sep 28, 2026
Last pushed: Nov 3, 2026
Forks: 0
Open issues: 0
Project activity: Active

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 1 note

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
58 network referencesin 12 files: prompts/RESEARCH_AND_TOOL_ROUTING.md:102 PROGRESS.md:11 evals/research-2026-11-03.md:9 and 9 more
1 obfuscation signalin 1 file: evals/real-cases/csv-total/case.json:12
No instruction overrides
25 executable scriptsin 25 files: evals/real-cases/csv-total/before.mjs:1 evals/real-cases/csv-total/candidate.mjs:1 evals/real-cases/line-summary/candidate.mjs:1 and 22 more
4 references to secretsin 4 files: .gitignore:11 prompts/RESEARCH_AND_TOOL_ROUTING.md:85 scripts/validate-toolkit.mjs:719 and 1 more
No requests to vote in Hot

Show all 88 signals by file

`.gitignore`

Access to secretsline 11
```
[Credential-related source omitted]
```

`PROGRESS.md`

Network accessline 11

| Publication | 3.2.0 source published to public main on 2026-10-03; exact source commit and hosted CI verified below | | Prior verification | 3.0.3: 40 tests and 12 representative generator cases passed on macOS arm64 / Node 26.8.1 | | Pri

Network accessline 12

| Prior verification | 3.0.3: 40 tests and 12 representative generator cases passed on macOS arm64 / Node 26.8.1 | | Prior hosted CI | 9/9 jobs passed on Linux, macOS and Windows with Node 20, 22 and 24: https://github.com/yanuarihsanxz-tec

Network accessline 13

| Prior hosted CI | 9/9 jobs passed on Linux, macOS and Windows with Node 20, 22 and 24: https://github.com/yanuarihsanxz-tech/prd-toolkit/actions/runs/36367364046 |

Network accessline 14

| Prior public inventory | https://github.com/yanuarihsanxz-tech/prd-toolkit; 70 canonical files verified on GitHub on 2026-09-28 |

Network accessline 40

- [Spec Kit contribution guide](https://github.com/github/spec-kit/blob/main/CONTRIBUTING.md): adopt focused changes, reproducible checks and updated user documentation.

Network accessline 41

- [OpenSpec onboarding](https://github.com/Fission-AI/OpenSpec/blob/main/docs/README.md): make the distinction between terminal commands and agent instructions explicit.

Network accessline 42

- [GSD contribution guide](https://github.com/gsd-build/get-shit-done/blob/main/CONTRIBUTING.md): adopt bug/improvement categories and concrete acceptance evidence; do not add its mandatory approval process to small fixes.

Network accessline 43

- [GitHub Mermaid support](https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/creating-diagrams): use Markdown Mermaid blocks without adding a diagram service.

Network accessline 101

Public source commit: `19445796ca0e2981081cf898adab8c8b872d0007`. GitHub Actions [run 37081441088](https://github.com/yanuarihsanxz-tech/prd-toolkit/actions/runs/37081441088)

Network accessline 102

Actions [run 37081441088](https://github.com/yanuarihsanxz-tech/prd-toolkit/actions/runs/37081441088)

`README.md`

Network accessline 20

git clone https://github.com/yanuarihsanxz-tech/prd-toolkit.git

Network accessline 43

Use PRD Maker from https://github.com/yanuarihsanxz-tech/prd-toolkit.git for this project.

`docs/DISTRIBUTION.md`

Network accessline 53

The published repository is [yanuarihsanxz-tech/prd-toolkit](https://github.com/yanuarihsanxz-tech/prd-toolkit).

Network accessline 54

[yanuarihsanxz-tech/prd-toolkit](https://github.com/yanuarihsanxz-tech/prd-toolkit).

`docs/GETTING_STARTED.md`

Network accessline 83

Codex documents project discovery from `.agents/skills` and supports symlinked skill directories. Start a new target chat and explicitly invoke `$prd-maker`, or ask to prepare a PRD. See [official Codex skill discovery](https://learn.chatgp

Network accessline 85

or ask to prepare a PRD. See [official Codex skill discovery](https://learn.chatgpt.com/docs/build-skills).

Network accessline 87

For Claude Code, export instead to `target/.claude/skills/prd-maker`, then invoke `/prd-maker`. This path and invocation follow [Claude Code's skill documentation](https://code.claude.com/docs/en/skills).

Network accessline 88

invoke `/prd-maker`. This path and invocation follow [Claude Code's skill documentation](https://code.claude.com/docs/en/skills). The [Agent Skills format](https://agentskills.io/specification) requires the

Network accessline 89

[Claude Code's skill documentation](https://code.claude.com/docs/en/skills).

Network accessline 90

The [Agent Skills format](https://agentskills.io/specification) requires the

`docs/PORTABLE_WORKFLOW.md`

Network accessline 50

Builders who already use [Ponytail](https://github.com/DietrichGebert/ponytail)

`evals/real-cases/README.md`

Network accessline 19

| Source | What `npm test` did | Exit | |---|---|---| | [3.2.0](https://github.com/yanuarihsanxz-tech/prd-toolkit/tree/250d72717b76029c8423913e2662950058c67af0) | All 113 project tests passed. Test discovery also executed the failing file i

Network accessline 20

|---|---|---| | [3.2.0](https://github.com/yanuarihsanxz-tech/prd-toolkit/tree/250d72717b76029c8423913e2662950058c67af0) | All 113 project tests passed. Test discovery also executed the failing file in the export. | 1 | | [3.3.0 implementat

Network accessline 21

| [3.2.0](https://github.com/yanuarihsanxz-tech/prd-toolkit/tree/250d72717b76029c8423913e2662950058c67af0) | All 113 project tests passed. Test discovery also executed the failing file in the export. | 1 |

Network accessline 22

| [3.3.0 implementation](https://github.com/yanuarihsanxz-tech/prd-toolkit/tree/c3d78b760f95e091c24ecfd03c6a083793e1bf1f) | All 131 project tests passed. The file in the export was never executed. | 0 |

`evals/real-cases/csv-total/before.mjs`

Executable scriptline 1
```
Executable file
```

`evals/real-cases/csv-total/candidate.mjs`

Executable scriptline 1
```
Executable file
```

`evals/real-cases/csv-total/case.json`

Possible obfuscationline 12

{ "id": "bom-header-only", "args": ["costs.csv"], "files": { "costs.csv": "<U+FEFF>item,amount\r\n" }, "expect": { "exit": 0, "json": { "rows": 0, "total": "0.00" }, "stderr": "" } },

`evals/real-cases/line-summary/candidate.mjs`

Executable scriptline 1
```
Executable file
```

`evals/research-2026-11-03.md`

Network accessline 9

| Primary source inspected | Relevant observation | Decision | |---|---|---| | [GitHub weekly Trending](https://github.com/trending?since=weekly) and [monthly Trending](https://github.com/trending?since=monthly) | Live HTML lists included H

Network accessline 10

|---|---|---| | [GitHub weekly Trending](https://github.com/trending?since=weekly) and [monthly Trending](https://github.com/trending?since=monthly) | Live HTML lists included Hallmark, Impeccable, Cloudflare's security-audit skill, Superpo

Network accessline 11

| [GitHub weekly Trending](https://github.com/trending?since=weekly) and [monthly Trending](https://github.com/trending?since=monthly) | Live HTML lists included Hallmark, Impeccable, Cloudflare's security-audit skill, Superpowers and other

Network accessline 12

| [Spec Kit README](https://github.com/github/spec-kit/blob/main/README.md) | Explicit operation entry points and multiple agent integration routes | Adopt a single portable CLI and explicit operation selection over existing canonical files

Network accessline 13

| [OpenSpec README](https://github.com/Fission-AI/OpenSpec/blob/main/README.md) | Existing-project changes are a first-class workflow with concrete scenarios | Keep the existing change contract; prove it with a retained CSV defect and an un

Network accessline 14

| [Karpathy autoresearch](https://github.com/karpathy/autoresearch) | Small editable scope and a fixed evaluation boundary make iteration observable | Add explicit behavioral case execution and source-identified results. This is an adaptati

Network accessline 15

| [Ponytail skill](https://github.com/DietrichGebert/ponytail/blob/main/skills/ponytail/SKILL.md) | Reuse existing code, then the standard library, and keep necessary verification | Reuse current validators and layouts; add no dependencies

Network accessline 21

On a maintainer host, the Codex CLI installed and listed Ponytail 5.3.3 as enabled. Its main skill matched the upstream Git blob at [the inspected revision](https://github.com/DietrichGebert/ponytail/tree/96608e078b2d5ea607c5c3b8b5a54d1c1fb

Network accessline 22

enabled. Its main skill matched the upstream Git blob at [the inspected revision](https://github.com/DietrichGebert/ponytail/tree/96608e078b2d5ea607c5c3b8b5a54d1c1fba6846). This installation was separate from the toolkit trials. Their resul

Network accessline 23

[the inspected revision](https://github.com/DietrichGebert/ponytail/tree/96608e078b2d5ea607c5c3b8b5a54d1c1fba6846).

`package.json`

Executable scriptline 1
```
Executable file
```

`prompts/RESEARCH_AND_TOOL_ROUTING.md`

Access to secretsline 85
```
[Credential-related source omitted]
```

Network accessline 102

| Candidate | Useful capability | Decision for this toolkit | Material reason | |---|---|---|---| | [Agent Specification Toolkit](https://github.com/hmbseaotter/agent-specification-toolkit) | EARS-style observable requirements | Adopt the w

Network accessline 103

|---|---|---|---| | [Agent Specification Toolkit](https://github.com/hmbseaotter/agent-specification-toolkit) | EARS-style observable requirements | Adopt the wording pattern locally, without installing the toolkit | Improves event/state ac

Network accessline 104

| [Agent Specification Toolkit](https://github.com/hmbseaotter/agent-specification-toolkit) | EARS-style observable requirements | Adopt the wording pattern locally, without installing the toolkit | Improves event/state acceptance precision

Network accessline 105

| [EAI Agent Toolkit](https://github.com/eai-org/agent-toolkit) | Ticket-to-implementation checking | Adopt the conformance-audit pattern locally | Directly closes the PRD-to-code evidence gap without importing a second skill catalog |

Network accessline 106

| [RTK](https://github.com/rtk-ai/rtk) | Compresses supported command output before it reaches the agent | Optional only after a measured implementation-phase benchmark | It reduces shell-output bytes, not all tokens, and adds a binary/inte

Network accessline 107

| [Headroom](https://github.com/headroomlabs-ai/headroom) | Tool-output and context compression through proxy, wrapper, or MCP routes | Experimental opt-in, not core | Long-session savings may be useful, but compression can hide diagnostic

Network accessline 108

| [Superpowers](https://github.com/obra/superpowers) | Full brainstorming, planning, TDD, and review methodology | Do not install for the canonical flow | It duplicates discovery, PRD, planning, execution, and review stages already owned he

Network accessline 126

| Candidate | Observed upstream capability | Decision for this toolkit | |---|---|---| | [Ponytail skill](https://raw.githubusercontent.com/DietrichGebert/ponytail/main/skills/ponytail/SKILL.md) | Reuse/stdlib/native-first coding with persi

Network accessline 127

|---|---|---| | [Ponytail skill](https://raw.githubusercontent.com/DietrichGebert/ponytail/main/skills/ponytail/SKILL.md) | Reuse/stdlib/native-first coding with persistent intensity modes | Keep the useful minimality principles in our exis

Network accessline 128

| [Ponytail skill](https://raw.githubusercontent.com/DietrichGebert/ponytail/main/skills/ponytail/SKILL.md) | Reuse/stdlib/native-first coding with persistent intensity modes | Keep the useful minimality principles in our existing workflow;

Network accessline 129

| [Caveman](https://github.com/JuliusBrussee/caveman) | Shorter output prose; upstream warns total cost can rise from added input | Plain concise status is sufficient; no always-on installation or claimed session savings |

Network accessline 130

| [Honey](https://github.com/Green-PT/honey-for-devs) | Code/prose reduction plus optional structured handoff and output-compression tools; upstream reports model-dependent costs | Keep exact contracts and ordinary Markdown/JSON; no new enc

Network accessline 131

| [Reasonix](https://github.com/esengine/DeepSeek-Reasonix) | Configurable coding runtime with provider/tool/plugin setup | Retain the existing optional adapter; do not replace the active host or auto-install a second runtime |

Network accessline 132

| [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) | Plugin-oriented runtime; upstream currently labels it developer preview with breaking changes | Optional runtime choice only; adds no required PRD capability to this lo

Network accessline 133

| [Codex skill discovery](https://learn.chatgpt.com/docs/build-skills) | Skills load from supported locations; folder references are not installation | Provide root SKILL.md for explicit use and a PRD-local builder entry; actual installed d

`schemas/generator-regression.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/prd-frontmatter.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/task-plan.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`schemas/task-state.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`scripts/authority-policy.mjs`

Executable scriptline 1
```
Executable file
```

`scripts/compare-prd.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/evaluate.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/export-toolkit.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/local-task-runner.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/prd.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/preview-prd.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/run-tests.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/validate-prd.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```

`scripts/validate-toolkit.mjs`

Executable scriptline 1
```
#!/usr/bin/env node
```
Access to secretsline 719
```
[Credential-related source omitted]
```

`tests/authority-policy.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/change-integration.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/compare-prd.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/distribution.test.mjs`

Executable scriptline 1
```
Executable file
```
Access to secretsline 45
```
[Credential-related source omitted]
```

`tests/evaluate.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/local-task-runner.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/prd.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/preview-prd.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/real-cases.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/validate-prd.test.mjs`

Executable scriptline 1
```
Executable file
```

`tests/validate-toolkit.test.mjs`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 78 facts

Network access in prose of documentationPROGRESS.md:11Low confidence
Network access in prose of documentationPROGRESS.md:12Low confidence
Network access in prose of documentationPROGRESS.md:13Low confidence
Network access in prose of documentationPROGRESS.md:14Low confidence
Network access in prose of documentationPROGRESS.md:40Low confidence
Network access in prose of documentationPROGRESS.md:41Low confidence
Network access in prose of documentationPROGRESS.md:42Low confidence
Network access in prose of documentationPROGRESS.md:43Low confidence
Network access in prose of documentationPROGRESS.md:101Low confidence
Network access in prose of documentationPROGRESS.md:102Low confidence
Network access in code of documentationREADME.md:20Low confidence
Network access in code of documentationREADME.md:43Low confidence
Network access in prose of documentationdocs/DISTRIBUTION.md:53Low confidence
Network access in prose of documentationdocs/DISTRIBUTION.md:54Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:83Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:85Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:87Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:88Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:89Low confidence
Network access in prose of documentationdocs/GETTING_STARTED.md:90Low confidence
Network access in prose of documentationdocs/PORTABLE_WORKFLOW.md:50Low confidence
Network access in prose of documentationevals/real-cases/README.md:19Low confidence
Network access in prose of documentationevals/real-cases/README.md:20Low confidence
Network access in prose of documentationevals/real-cases/README.md:21Low confidence
Network access in prose of documentationevals/real-cases/README.md:22Low confidence
Executable script in a comment of a file that runsevals/real-cases/csv-total/before.mjs:1Low confidence
Executable script in code of a file that runsevals/real-cases/csv-total/candidate.mjs:1High confidence
Executable script in code of a file that runsevals/real-cases/line-summary/candidate.mjs:1High confidence
Network access in prose of documentationevals/research-2026-11-03.md:9Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:10Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:11Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:12Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:13Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:14Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:15Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:21Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:22Low confidence
Network access in prose of documentationevals/research-2026-11-03.md:23Low confidence
Executable script in code of a file that runspackage.json:1High confidence
Access to secrets in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:85Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:102Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:103Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:104Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:105Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:106Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:107Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:108Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:126Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:127Low confidence
Network access in prose of documentationprompts/RESEARCH_AND_TOOL_ROUTING.md:128Low confidence

and 28 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path CLAUDE.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

yanuarihsanxz-tech/prd-toolkit

History

SKILL.md

prompts/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

prd-maker

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

prd-generator

Frontmatter

SKILL.md

Reference documents

The playbook

Files

Skills included

Repository facts

Before you install

.gitignore

PROGRESS.md

README.md

docs/DISTRIBUTION.md

docs/GETTING_STARTED.md

docs/PORTABLE_WORKFLOW.md

evals/real-cases/README.md

evals/real-cases/csv-total/before.mjs

evals/real-cases/csv-total/candidate.mjs

evals/real-cases/csv-total/case.json

evals/real-cases/line-summary/candidate.mjs

evals/research-2026-11-03.md

package.json

prompts/RESEARCH_AND_TOOL_ROUTING.md

schemas/generator-regression.schema.json

schemas/prd-frontmatter.schema.json

schemas/task-plan.schema.json

schemas/task-state.schema.json

scripts/authority-policy.mjs

scripts/compare-prd.mjs

scripts/evaluate.mjs

scripts/export-toolkit.mjs

scripts/local-task-runner.mjs

scripts/prd.mjs

scripts/preview-prd.mjs

scripts/run-tests.mjs

scripts/validate-prd.mjs

scripts/validate-toolkit.mjs

tests/authority-policy.test.mjs

tests/change-integration.test.mjs

tests/compare-prd.test.mjs

tests/distribution.test.mjs

tests/evaluate.test.mjs

tests/local-task-runner.test.mjs

tests/prd.test.mjs

tests/preview-prd.test.mjs

tests/real-cases.test.mjs

tests/validate-prd.test.mjs

tests/validate-toolkit.test.mjs

How the signals fit together

Works with

You might also use

franklinxkk/ai-delivery-spec

imxv/Pretty-mermaid-skills

anombyte93/prd-taskmaster

adand-91/gpt-6-astra-skill

Agile-V/agile_v_skills

ZeroPointRepo/CRHQ-PRDs

`SKILL.md`

`prompts/SKILL.md`

`.gitignore`

`PROGRESS.md`

`README.md`

`docs/DISTRIBUTION.md`

`docs/GETTING_STARTED.md`

`docs/PORTABLE_WORKFLOW.md`

`evals/real-cases/README.md`

`evals/real-cases/csv-total/before.mjs`

`evals/real-cases/csv-total/candidate.mjs`

`evals/real-cases/csv-total/case.json`

`evals/real-cases/line-summary/candidate.mjs`

`evals/research-2026-11-03.md`

`package.json`

`prompts/RESEARCH_AND_TOOL_ROUTING.md`

`schemas/generator-regression.schema.json`

`schemas/prd-frontmatter.schema.json`

`schemas/task-plan.schema.json`

`schemas/task-state.schema.json`

`scripts/authority-policy.mjs`

`scripts/compare-prd.mjs`

`scripts/evaluate.mjs`

`scripts/export-toolkit.mjs`

`scripts/local-task-runner.mjs`

`scripts/prd.mjs`

`scripts/preview-prd.mjs`

`scripts/run-tests.mjs`

`scripts/validate-prd.mjs`

`scripts/validate-toolkit.mjs`

`tests/authority-policy.test.mjs`

`tests/change-integration.test.mjs`

`tests/compare-prd.test.mjs`

`tests/distribution.test.mjs`

`tests/evaluate.test.mjs`

`tests/local-task-runner.test.mjs`

`tests/prd.test.mjs`

`tests/preview-prd.test.mjs`

`tests/real-cases.test.mjs`

`tests/validate-prd.test.mjs`

`tests/validate-toolkit.test.mjs`