project-development

An agent skill by muratcankoylan, from muratcankoylan/Agent-Skills-for-Context-Engineering. Tags: analytics, automation, developer-tools, product-strategy, strategy.

What it does

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill project-development

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering
cp -r Agent-Skills-for-Context-Engineering/skills/project-development ~/.claude/skills/project-development

Safety box score

Grade B, low risk: 11 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is mostly methodology text plus a runnable Python batch-pipeline template for LLM projects. Its main blast radius is local: it creates, overwrites, and can delete staged artifacts under `data/{batch_id}` and `output/{batch_id}`, and it can run an entire pipeline end-to-end in one command. It does not ship secrets handling, privilege escalation, or active network-fetch code.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	`scripts/pipeline_template.py` is a runnable CLI (`if __name__ == "__main__": main()`) with threaded processing and parsing, but it does not execute arbitrary shell commands or eval code.
Network access	0 (none)	No active outbound requests ship; the only network-looking items are documentation URLs and a commented-out Anthropic API example in `call_llm`.
Filesystem reach	1 (low)	The template writes and deletes only inside the batch/output trees (`open(..., "w")`, `filepath.unlink()` in `stage_clean`), so the scope is limited to project-local state.
Secrets & credentials	0 (none)	There is no code that reads `.env`, keychains, browser sessions, tokens, or passwords, and the docs do not ask for secrets.
Privilege & persistence	0 (none)	No `sudo`, global installs, service registration, shell startup edits, or OS-level settings appear in the shipped files.
Instruction hijack surface	0 (none)	The skill contains prompt-formatting guidance only; it does not instruct the agent to ignore its rules, hide content, or follow untrusted remote instructions.
Irreversible actions	1 (low)	The CLI can run `acquire -> prepare -> process -> parse -> render` in one shot via `all`, but it does not send messages, pay, deploy, or contact third parties.
Transparency	0 (none)	All shipped files are readable plain text; there are no binaries, base64 blobs, or downloaded installers.

Before installing

Read `scripts/pipeline_template.py` and confirm the `clean` stage only deletes what you expect under `data/{batch_id}`.
Run `python scripts/pipeline_template.py estimate --batch-id <scratch>` first, then `all --limit 1` in a test batch.
If you plan to replace the mock `call_llm`, inspect that function before use; that is where real API/network behavior would enter.
Verify the `output/{batch_id}` location is acceptable, since render writes there automatically.

Rated 2026-10-20 by an automated review of 4 files from the skill's repository.

Source

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering (all skills from this repository)
Path: skills/project-development/SKILL.md
Branch: main
Updated: 2026-09-19

advanced-evaluation — This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration.
memory-systems — This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity.
bdi-mental-states — This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations.
context-compression — This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization.
context-degradation — This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion.
context-optimization — This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning.