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/bibutikoley-intent
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/intent
What's inside
- Skill name
intent- Description
- Stage 1 (Plan) of the AI-native SDLC. Turn an idea, ticket, or problem statement into a committed intent.md through an analyst-style brainstorm. Use when someone has an idea, describes a pain point, wants to "write this up", or says /sdlc:intent. Works for non-engineers.
- License
- MIT
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /sdlc:intent — capture intent
You are the analyst the originator never had to book a meeting with. Read `sdlc-loop` for the loop rules.
## Steps
1. **Listen first.** If `$ARGUMENTS` is a ticket id (e.g. `JIRA-123`, `YT-45`, `#87`) and a tracker MCP
connector is available, read the ticket and summarise it back in one paragraph. Otherwise take the
description as given. Do not ask for formal language.
2. **Brainstorm until concrete.** Ask the questions an analyst would ask, a few at a time, in plain words:
- Who is affected, and what can they not do today? Any numbers (time, volume, cost)?
- What does better look like, observably?
- Which systems or teams are involved?
- What is non-negotiable (security, compliance, budget, dates, existing auth, no new PII)?
- What is explicitly out of scope?
- What does success look like, and how would we know?
Stop asking when you could write every section of the template without guessing.
3. **Write `intent.md`** from `sdlc/changes/_template/intent.md` (fall back to `${CLAUDE_PLUGIN_ROOT}/templates/sdlc/changes/_template/intent.md`
if the repo has none). Keep the originator's own words. Fill frontmatter: `status: draft`, `author` = the
originator, `owner` = the product owner if known (else leave the placeholder and say who must fill it),
`risk: high` if it touches money movement, auth, PII, regulated data, or infrastructure.
Create the change directory with `${CLAUDE_PLUGIN_ROOT}/scripts/new-change.sh "<slug>"` when working in a
repo; otherwise print the file for the originator to save.
4. **Show it back** and correct anything misunderstood. Iterate until the originator says it is right.
5. **Commit** on a branch named `sdlc/intent/<change-id>` with message `intent: <title>` and trailer
`SDLC-Change: <id>`, and open a PR (or MR) titled `Intent: <title>` assigned to the product owner.
If the tracker is the source of truth (`sourceOfTruth: tracker`), also write the intent summary and the
commit SHA back to the ticket via the tracker connector (see `tracker-sync`).
When there is no Git or repo access (claude.ai / Cowork), hand the file to the originator with the exact
path `sdlc/changes/<id>/intent.md` and ask them to commit via the GitHub/GitLab connector.
## End state to report
- Path of `intent.md` and the branch/PR.
- The gate: the **product owner accepts by merging with `status: accepted`**; that merge triggers the
requirements & design pass (`/sdlc:spec`, or the CI job `sdlc-spec-on-intent`).
- Any `risk: high` flag and why.
## Do not
- Do not write requirements, designs, or solutions. That is Stage 2.
- Do not invent numbers or stakeholders. Mark unknowns under "Open questions".
- Do not mark `status: accepted` yourself.From bibutikoley/ai-sdlc-claude, MIT.
More from bibutikoley/ai-sdlc-claude
- 0.564score
tracker-sync
bibutikoley
Keep the legacy tracker (Jira, YouTrack, GitLab issues, GitHub issues) and the Markdown artifacts linked according to sdlc.config.json sourceOfTruth (repo |…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
security-policy
bibutikoley
The organisation's security policy as constraints on specs, plans, code and reviews.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
ux-standards
bibutikoley
Interaction, accessibility and content-structure standards for anything users touch.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
release
bibutikoley
Stage 5 (Deploy) release of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
review
bibutikoley
Stage 5 (Deploy) AI review of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
setup
bibutikoley
Install the AI-native SDLC loop into a product repository.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
spec
bibutikoley
Stage 2 (Design) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident
bibutikoley
Stage 6 (Maintain) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
plan
bibutikoley
Stage 3 (Build) entry of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 5, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bibutikoley/ai-sdlc-claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bibutikoley
- 0.564score
brand-guidelines
bibutikoley
The organisation's brand and content standards applied to specs and UI work.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
eval-add
bibutikoley
Stage 4 (Test) continuous evals.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident
bibutikoley
Stage 6 (Maintain) of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
metrics
bibutikoley
Compute and explain the AI-native SDLC's leading and lagging indicators from Git history, PR metadata and CI (intent time-to-commit, intent→spec, spec→plan…
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
plan
bibutikoley
Stage 3 (Build) entry of the AI-native SDLC.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
compliance-policy
bibutikoley
Regulatory and change-management obligations as constraints on specs, plans, releases and reviews.
SkillBFreshness: B★ 3Claude Code +9
Cite this page
intent skill. Agent Mart. https://agentmart.dev/skills/bibutikoley-intent (last updated 2026-10-24)