Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Context Engineering · kdlbs | DecimalAI

agent toolingby kdlbs

Context Engineering

kdlbs/context-engineering

Source kdlbs/kandev ↗License AGPL-3.0

Curate the right project context before coding or debugging.

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 10/9/2026

What it changes

Passed 20 of 20 test cases with the skill, and 12 of 20 without it.

Without skill60%

With skill100%

Checks it passed that the model alone missed

Place rules files at sequence position 1.
Specify `apps/backend/AGENTS.md` under RULES:.
Include `/e2e` guidance for user interface flows.

and 14 more in the full report

8 fixed12 passed either way0 still failing0 broke2 errored

Pass-rate lift: +40 pp
Tokens: +25%
Agent turns: 0%
Response time: -48%

Model gemini-3.6-flashMeasured 10/9/2026v520 of 22 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/kdlbs-context-engineering/SKILL.md https://app.decimal.ai/s/kdlbs-context-engineering/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add kdlbs-context-engineering, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/kdlbs-context-engineering/ and pins it in .decimal/skills.lock

decimalai skills add kdlbs-context-engineering

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/kdlbs-context-engineering/SKILL.md https://app.decimal.ai/s/kdlbs-context-engineering/SKILL.md

Raw file: /s/kdlbs-context-engineering/SKILL.md ↗ · machine-readable summary at /s/kdlbs-context-engineering.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We are modifying the React user profile card component in `apps/web/components/profile`. Which domain guidance tags should be included in the context planning step?

What was checked, without and with the skill
Checked	Without skill	With skill
Include `/mobile-parity` guidance when updating frontend components.	Missed	Passed
Include `/e2e` guidance for user interface flows.	Missed	Passed

case-14 · gemini-3.6-flash · 10/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md96 linessingle file

Context Engineering

Feed the agent the right information at the right time. Too little context causes invented APIs; too much context hides the relevant pattern.

Context Order

Rules: root AGENTS.md, scoped AGENTS.md, and any invoked skills.
Specifications and delivery: the owning system README.md, relevant requirements, system designs, ADRs, plan.md, and the current work order.
Source: exact files to modify, related tests, and one similar implementation.
Evidence: focused error output, failing test name, CI summary, screenshots, or logs.
Conversation: current user request and any confirmed decisions.

Kandev Loading Checklist

Before running shell commands, resolve every @path import in the root or scoped AGENTS.md/CLAUDE.md files and read the referenced instructions. If an imported file is unavailable, note the missing guidance and continue with the best available local instructions.

Before changing code:

Read the scoped AGENTS.md for the subtree you will touch, e.g. apps/backend/AGENTS.md, apps/web/AGENTS.md, or integration-specific guidance.
Use rg to find existing patterns before inventing one.
Read the file you will edit and nearby tests.
For product features, read docs/specs/README.md, the owning system README.md, adjacent system README files with similar capability names, and only the relevant requirement and system-design files. Choose the owner from the durable contract, not the affected code layer. Use python3 scripts/list-docs.py specs --format paths to find documents. During migration, add --kind legacy to find a legacy source.
When implementing from a plan, read plan.md for orientation and only the current work order. Follow its REQ-*, AC-*, and system-design references.
Dependency, sibling, and stacked PR references are snapshots. Resolve the current dependency and base heads before implementation and again before final fixup; if a dependency moved or landed, re-read the affected requirements, designs, contracts, and traceability links.
For frontend/UI, include /mobile-parity and /e2e guidance when applicable.
For OpenAI/API docs or other fast-moving dependencies, use official docs or primary sources.

Selective Context Patterns

Track record

Benchmark

20 / 20

test cases passed, vs 12 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

kdlbs / kandev

.agents/skills/context-engineering/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 10/9/2026Version v5

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Context Engineering

Context Order

Kandev Loading Checklist

Selective Context Patterns

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills