Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Dutch public-tender CLI with offline search, document corpus, and the sub-threshold long tail TED never sees.
.claude/skills/mvanhorn-pp-tenderned/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 137% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 37% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -21% | 0% |
<!-- GENERATED FILE — DO NOT EDIT. This file is a verbatim mirror of library/sales-and-crm/tenderned/SKILL.md, regenerated post-merge by tools/generate-skills/. Hand-edits here are silently overwritten on the next regen. Edit the library/ source instead. See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
This skill drives the tenderned-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:bash npx -y @mvanhorn/printing-press-library install tenderned --cli-only
tenderned-pp-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer):
bashgo install github.com/mvanhorn/printing-press-library/library/sales-and-crm/tenderned/cmd/tenderned-pp-cli@latest
If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
buyers — Browse contracting authorities (aanbestedende diensten) — Dutch public buyers
tenderned-pp-cli buyers get — Fetch one contracting authority by IDtenderned-pp-cli buyers list — List Dutch contracting authorities (paginated)docs — List and download tender documents (bestek, PvE, evaluation criteria, Q&A)
tenderned-pp-cli docs download — Download all documents for one publication as a zip archivetenderned-pp-cli docs get — Download a single document's binary content (PDF/Word/etc.)tenderned-pp-cli docs list — List attached documents for one publicationnotices — Search, list and fetch tender notices (aankondigingen) from TenderNed — mirrors 'eu-tenders notices' for the Dutch market
tenderned-pp-cli notices get — Fetch full structured metadata for one publicationtenderned-pp-cli notices list — Search and list tender publications with rich filters (CPV, dates, buyer, procedure, scope)When you know what you want to do but not which command does it, ask the CLI directly:
bashtenderned-pp-cli which "<capability in your own words>"
which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.
No authentication required.
Run tenderned-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
--select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:bash tenderned-pp-cli buyers list --agent --select id,name,status
--dry-run shows the request without sendingCommands that read from the local store or the API wrap output in a provenance envelope:
json{ "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": <data> }
Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
tenderned-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
tenderned-pp-cli feedback --stdin < notes.txt
tenderned-pp-cli feedback list --json --limit 10Entries are stored locally at ~/.local/share/tenderned-pp-cli/feedback.jsonl. They are never POSTed unless TENDERNED_FEEDBACK_ENDPOINT is set AND either --send is passed or TENDERNED_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect | |------|--------| | stdout | Default; write to stdout only | | file:<path> | Atomically write output to <path> (tmp + rename) | | webhook:<url> | POST the output body to the URL (application/json or application/x-ndjson when --compact) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
tenderned-pp-cli profile save briefing --json
tenderned-pp-cli --profile briefing buyers list
tenderned-pp-cli profile list --json
tenderned-pp-cli profile show briefing
tenderned-pp-cli profile delete briefing --yesExplicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning | |------|---------| | 0 | Success | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show tenderned-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it:
bashclaude mcp add tenderned-pp-mcp -- tenderned-pp-mcp
Verify: claude mcp list
which tenderned-pp-cliIf not found, offer to install (see Prerequisites at the top of this skill).
--agent flag:bash tenderned-pp-cli <command> [subcommand] [args] --agent
tenderned-pp-cli <command> --help.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,273 | 10,574 | +69% | 1 | 1 | 0% | 327 | 2,237 | +584% | 0 | 0 | — |
case-02 | fail→fail | 14,947 | 7,389 | -51% | 1 | 1 | 0% | 2,067 | 2,369 | +15% | 0 | 0 | — |
case-03 | fail→fail | 12,493 | 4,920 | -61% | 1 | 1 | 0% | 2,363 | 2,242 | -5% | 0 | 0 | — |
case-04 | fail→pass | 8,127 | 3,008 | -63% | 1 | 1 | 0% | 1,055 | 2,502 | +137% | 0 | 0 | — |
case-05 | pass→pass | 7,519 | 4,287 | -43% | 1 | 1 | 0% | 1,194 | 2,608 | +118% | 0 | 0 | — |
case-06 | pass→pass | 5,364 | 2,844 | -47% | 1 | 1 | 0% | 921 | 2,428 | +164% | 0 | 0 | — |
case-07 | fail→pass | 13,061 | 2,803 | -79% | 1 | 1 | 0% | 2,139 | 2,414 | +13% | 0 | 0 | — |
case-08 | fail→pass | 11,318 | 2,708 | -76% | 1 | 1 | 0% | 1,872 | 2,509 | +34% | 0 | 0 | — |
case-09 | fail→pass | 10,417 | 5,356 | -49% | 1 | 1 | 0% | 1,792 | 2,449 | +37% | 0 | 0 | — |
case-10 | fail→pass | 20,754 | 3,502 | -83% | 1 | 1 | 0% | 3,157 | 2,494 | -21% | 0 | 0 | — |
case-11 | fail→pass | 10,316 | 2,781 | -73% | 1 | 1 | 0% | 1,682 | 2,573 | +53% | 0 | 0 | — |
case-12 | pass→pass | 8,736 | 2,597 | -70% | 1 | 1 | 0% | 1,227 | 2,339 | +91% | 0 | 0 | — |
case-13 | fail→fail | 9,986 | 5,452 | -45% | 1 | 1 | 0% | 1,831 | 2,262 | +24% | 0 | 0 | — |
case-14 | fail→pass | 11,520 | 3,304 | -71% | 1 | 1 | 0% | 1,907 | 2,561 | +34% | 0 | 0 | — |
case-15 | fail→pass | 17,311 | 2,824 | -84% | 1 | 1 | 0% | 2,042 | 2,502 | +23% | 0 | 0 | — |
case-16 | fail→pass | 10,699 | 1,930 | -82% | 1 | 1 | 0% | 1,620 | 2,273 | +40% | 0 | 0 | — |
case-17 | fail→pass | 11,081 | 3,238 | -71% | 1 | 1 | 0% | 1,866 | 2,578 | +38% | 0 | 0 | — |
case-18 | fail→pass | 7,992 | 2,830 | -65% | 1 | 1 | 0% | 1,201 | 2,457 | +105% | 0 | 0 | — |
case-19 | fail→pass | 14,846 | 2,516 | -83% | 1 | 1 | 0% | 1,781 | 2,363 | +33% | 0 | 0 | — |
case-20 | fail→pass | 11,224 | 2,360 | -79% | 1 | 1 | 0% | 1,978 | 2,375 | +20% | 0 | 0 | — |
case-21 | fail→fail | 9,213 | 3,201 | -65% | 1 | 1 | 0% | 1,596 | 2,549 | +60% | 0 | 0 | — |
case-22 | fail→pass | 7,203 | 3,251 | -55% | 1 | 1 | 0% | 1,302 | 2,448 | +88% | 0 | 0 | — |
case-23 | fail→pass | 15,229 | 3,721 | -76% | 1 | 1 | 0% | 2,330 | 2,459 | +6% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +65 percentage points is the difference between those two pass rates over the 19 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.