Orchestration
numman-ali/n-skills
Multi-agent orchestration for complex tasks. An agent skill from numman-ali/n-skills.
Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end.
Install Incremental Implementation
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/incremental-implementation .claude/skills/incremental-implementation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .claude/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/incremental-implementation .agents/skills/incremental-implementation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .agents/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/incremental-implementation .cursor/skills/incremental-implementation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .cursor/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mohitagw15856/pm-claude-skills.git --path skills/incremental-implementation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/incremental-implementation .gemini/skills/incremental-implementation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .gemini/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/incremental-implementation .github/skills/incremental-implementation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .github/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills incremental-implementation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/incremental-implementation .opencode/skills/incremental-implementation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "incremental-implementation" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/incremental-implementation into .opencode/skills/incremental-implementation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "incremental-implementation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
incremental-implementation- GitHub stars
- 1.4k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 602 words
- Files
- 1
- Skills in repo
- 1,322
- Repo updated
- First seen
- Licence
- MIT
At a glance
Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end.
- Works in 6 steps: Slice vertically to working states, not… → Separate behaviour-preserving from… → Verify at every increment — the same… → …
- Implementing multi-part features
- SKILL.md covers What This Skill Produces, Increment Method, Output Format and Quality Checks, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Incremental Implementation is an agent skill from mohitagw15856/pm-claude-skills. Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end. Use when implementing multi-part features, refactoring anything load-bearing, making large mechanical changes, or when past work produced huge diffs that were wrong somewhere unfindable. Produces the same end state as the big bang, reached through verified checkpoints you can stop at, ship from, or roll back to.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Task breakdown and Refactoring. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Implementing multi-part features
- Refactoring anything load-bearing
- Making large mechanical changes
- Past work produced huge diffs that were wrong somewhere unfindable
Example prompts
- “/incremental-implementation”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Slice vertically to working states, not horizontally to layers. "Data layer, then logic, then UI" means nothing works until everything…
- Separate behaviour-preserving from behaviour-changing — always. The cardinal rule: refactor OR change behaviour in one increment, never…
- Verify at every increment — the same way. Green means: the relevant tests/build pass AND the previous increments' behaviour still holds…
- Migrate parallel, then cut over, then remove. For replacements: build the new alongside the old → migrate consumers one-by-one (each…
- When an increment goes red: fix or revert, within the increment. Never pile the next increment onto a broken state "to fix it all…
- Size to risk. Load-bearing/unfamiliar territory: smaller steps, verify obsessively. Well-trodden mechanical work: bigger steps are fine…
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Incremental Implementation loads about 1.2k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 602 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 602 words, ~1,179 tokens.
Download SKILL.mdSave it as
.claude/skills/incremental-implementation/SKILL.md (or your agent's skills folder).- name
- incremental-implementation
- description
- Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end. Use when implementing multi-part features, refactoring anything load-bearing, making large mechanical changes, or when past work produced huge diffs that were wrong somewhere unfindable. Produces the same end state as the big bang, reached through verified checkpoints you can stop at, ship from, or roll back to.
Incremental Implementation Skill
The big-bang failure is always the same story: three hours of changes, then "it doesn't work", then an hour of spelunking to find WHICH of forty edits broke it. Incremental work makes the last five minutes the only suspect, always. The discipline: every increment ends with the system working and verified — not "will work once the rest lands."
What This Skill Produces
- The target end state, reached via increments that were each verified green
- Stoppable points: any checkpoint is shippable, pausable, or a rollback target
- A change history where every step's intent is legible
Increment Method
- Slice vertically to working states, not horizontally to layers. "Data layer, then logic, then UI" means nothing works until everything does. Slice so each increment is a thin working slice: one endpoint end-to-end · one case handled fully · one call-site migrated. The test for a slice: after it lands, can you demonstrate something that works?
- Separate behaviour-preserving from behaviour-changing — always. The cardinal rule: refactor OR change behaviour in one increment, never both. Prepare-with-refactor (verify: everything still passes, nothing changed) → then the behaviour change lands small and legible. Mixing them makes every regression a two-variable mystery.
- Verify at every increment — the same way. Green means: the relevant tests/build pass AND the previous increments' behaviour still holds. Establish the verification command once, run it every increment. An increment without a green check is just a chunk of a big bang wearing increments' clothes.
- Migrate parallel, then cut over, then remove. For replacements: build the new alongside the old → migrate consumers one-by-one (each migration an increment) → only when the old has zero callers, delete it (its own increment). The both-exist window feels untidy; it's what makes every step reversible.
- When an increment goes red: fix or revert, within the increment. Never pile the next increment onto a broken state "to fix it all together" — that's the moment incremental discipline dies and the mystery diff is born. The whole point is that red has one suspect; keep it that way.
- Size to risk. Load-bearing/unfamiliar territory: smaller steps, verify obsessively. Well-trodden mechanical work: bigger steps are fine. If you can't predict what an increment will break, it's too big — split it.
Show full SKILL.md (232 more words)Show less
Output Format
Increment plan: [target end state]
| # | Increment (thin working slice) | Type | Verified by | Stoppable? |
|---|---|---|---|---|
| 1 | refactor-only / behaviour | [command/check] | ship / pause / rollback point |
The both-exist window (if migrating): [what coexists between steps N–M, and the cutover order]
Standing verification: [the command run after every increment]
(during execution, per increment: what landed → verification result → next)
Quality Checks
- Every increment ends in a demonstrated working state — no "works once the rest lands"
- No increment mixes refactoring with behaviour change
- The same verification ran green after each increment
- Any increment could serve as a stopping point without leaving wreckage
- Red states were fixed or reverted before the next increment began
Anti-Patterns
- Do not slice by layer — horizontal slices defer all verification to the end, which is the big bang with extra commits
- Do not "keep going" on a red state — stacking onto broken is how one bug becomes an archaeology dig
- Do not skip verification on 'trivial' increments — the trivial one is statistically where it breaks
- Do not delete the old path in the same increment as the last migration — cutover and removal are separate, reversible steps
- Do not let increments shrink into commit-theatre (40 one-line steps) — an increment is sized by verifiable meaning, not by smallness itself
Example Trigger Phrases
- "Build this feature in small verified steps."
- "Refactor anything load-bearing safely."
- "Make this large mechanical change incrementally."
- "Implement this multi-part feature without breaking things."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/incremental-implementation of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Incremental Implementation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Incremental Implementation this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Orchestrationnumman-ali/n-skills | 1.1k | — | ~7.7k | Automated safety check: Pass | Apache-2.0 | |
| Plan Modeespennilsen/pi | 122 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Filescope MCPadmica/FileScopeMCP | 302 | — | ~1.7k | Automated safety check: Pass | Proprietary | |
| Spec Driven Developzhu1090093659/spec_driven_develop | 984 | — | ~5.1k | Automated safety check: Pass | MIT |
Similar skills
Plan Mode
espennilsen/pi
Structured planning mode for AI agents working on coding and development tasks.
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
Filescope MCP
admica/FileScopeMCP
Codebase intelligence via FileScopeMCP — symbol lookup, dependency mapping, importance ranking, and semantic search.
Spec Driven Develop
zhu1090093659/spec_driven_develop
Automates pre-development workflow for large-scale complex tasks.
Gograph Go Repository Intelligence
ozgurcd/gograph
Gives an agent working in a Go codebase a structural view through a local MCP server: call graphs, blast-radius and impact analysis, and bounded first-call exploration.
More from mohitagw15856/pm-claude-skills
All 1,322 skills in this repoExit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Offer Comparison
mohitagw15856/pm-claude-skills
Compare two or more job offers as total-comp curves over four years — vesting cliffs, bonuses, 401(k) match, and the crossover year computed, not vibed.
Refinance Breakeven
mohitagw15856/pm-claude-skills
Compute the month a refinance actually starts saving money — payment delta, breakeven month, and total interest on both paths including the term-reset trap.
Rent Vs Buy
mohitagw15856/pm-claude-skills
Model rent-vs-buy honestly — year-by-year net position for both paths including the assumption everyone drops (the renter invests the difference), with a breakeven horizon instead of a verdict.
Related
Categories
Questions about Incremental Implementation
What does Incremental Implementation do?
Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end. Incremental Implementation is an agent skill from mohitagw15856/pm-claude-skills. Build in small, individually-verified increments that each leave the system working — instead of big-bang changes that fail mysteriously at the end.
When should I use Incremental Implementation?
Incremental Implementation fits situations like: implementing multi-part features; refactoring anything load-bearing; making large mechanical changes; past work produced huge diffs that were wrong somewhere unfindable.
How do I install Incremental Implementation in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a claude-code`. Or copy the skill folder (skills/incremental-implementation in mohitagw15856/pm-claude-skills) into .claude/skills/incremental-implementation in your project. Claude Code loads it when a task matches its description.
How do I install Incremental Implementation in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a codex`. Or copy the skill folder (skills/incremental-implementation in mohitagw15856/pm-claude-skills) into .agents/skills/incremental-implementation in your project. Codex loads it when a task matches its description.
Can I use Incremental Implementation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill incremental-implementation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/incremental-implementation, .gemini/skills/incremental-implementation, .github/skills/incremental-implementation and .opencode/skills/incremental-implementation in your project.
What does Incremental Implementation need to run?
SKILL.md names no scripts, command-line tools or credentials: Incremental Implementation is instructions for the agent only.
Does Incremental Implementation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Incremental Implementation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Incremental Implementation use?
Incremental Implementation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Incremental Implementation use?
About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Incremental Implementation?
Skills that share tags, products or a category with Incremental Implementation: Orchestration (numman-ali/n-skills, 1.1k stars), Plan Mode (espennilsen/pi, 122 stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars) and Filescope MCP (admica/FileScopeMCP, 302 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Incremental Implementation?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,431 GitHub stars. The repository holds 1,322 skills in this directory. The repository was last updated on October 7, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.